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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical interaction or manipulation of objects

    oai_token-act-pair · gpt-3.5-turbo

    actions involving physical manipulation or interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ontent
    -0.82
     Bast
    -0.78
     Equality
    -0.77
     redundancy
    -0.71
     suites
    -0.71
    Bah
    -0.71
    LIST
    -0.71
    CLUS
    -0.69
     Clash
    -0.66
     Surviv
    -0.66
    POSITIVE LOGITS
    tip
    1.17
     gently
    1.14
     fingers
    1.12
     finger
    1.03
     downwards
    1.03
     fingertips
    1.03
    poon
    1.01
     fingert
    1.01
     rubbing
    1.00
     protr
    1.00
    Act Density 0.373%

    No Known Activations