Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    themes of escape and protection from various threats or negative influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "from" or a word indicating escape

    np_acts-logits-general · gemini-2.0-flash

    escape from danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.71
    DebuggerNonUser
    -0.66
    TagMode
    -0.63
     INTERESAR
    -0.63
    ChromeDriver
    -0.59
    esModule
    -0.59
     prisonniers
    -0.59
    AlterField
    -0.57
     riuscito
    -0.57
    createComponent
    -0.56
    POSITIVE LOGITS
     onslaught
    0.95
     attacks
    0.95
     scrutiny
    0.92
     threats
    0.85
     pressures
    0.80
    attacks
    0.78
     attack
    0.75
     sudden
    0.75
     wrath
    0.74
     relentless
    0.72
    Act Density 0.502%

    No Known Activations