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

    Neuronpedia

    INDEX
    Explanations

    violent actions involving physical contact or objects

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to physical violence and objects associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rosso
    -0.82
     qualitative
    -0.74
     specificity
    -0.73
     autonomy
    -0.67
    KNOWN
    -0.66
     Alam
    -0.64
    Specific
    -0.64
     personalities
    -0.63
     conversions
    -0.63
    ITNESS
    -0.62
    POSITIVE LOGITS
     ledge
    1.10
     fence
    0.96
     mattress
    0.95
     bushes
    0.91
     pedest
    0.91
     sofa
    0.88
     railing
    0.88
    andel
    0.88
     stret
    0.87
     curtains
    0.87
    Act Density 0.299%

    No Known Activations