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

    Neuronpedia

    INDEX
    Explanations

    technical details and specifications related to software or computer systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tonsoft
    -0.90
    UnsafeEnabled
    -0.85
    CloseOperation
    -0.82
    ništvo
    -0.81
    ViewFeatures
    -0.81
    Enllaços
    -0.81
     الحره
    -0.80
     itſelf
    -0.78
     $_"
    -0.76
    theless
    -0.75
    POSITIVE LOGITS
     or
    0.46
    am
    0.45
    ™,
    0.45
    ®,
    0.44
    ™
    0.44
    ®
    0.44
    copyWith
    0.43
    Races
    0.43
     Die
    0.43
    <bos>
    0.43
    Act Density 1.962%

    No Known Activations