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

    Neuronpedia

    INDEX
    Explanations

    phrases centered around taking action or making decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     care
    -0.44
    故
    -0.44
    findpost
    -0.43
     soldati
    -0.43
    cabul
    -0.43
    []):
    -0.42
    пита
    -0.42
    Capture
    -0.41
    __:
    -0.41
    歴
    -0.41
    POSITIVE LOGITS
     leap
    1.00
    MemoryWarning
    0.82
    Autoritní
    0.76
     Leap
    0.75
     step
    0.75
     stance
    0.74
    leap
    0.73
    MigrationBuilder
    0.72
     plunge
    0.72
     stab
    0.71
    Act Density 0.123%

    No Known Activations