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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or functions performed by objects or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of entities or concepts described as playing active or representative roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chev
    -0.74
    rants
    -0.70
    rone
    -0.70
    eor
    -0.68
    ties
    -0.66
    olds
    -0.66
    tten
    -0.65
    tom
    -0.64
    yd
    -0.64
    ulous
    -0.63
    POSITIVE LOGITS
     intermediary
    1.13
     liaison
    0.96
     catalyst
    0.94
     deterrent
    0.94
     conduit
    0.92
     lookout
    0.92
     intermedi
    0.91
     condu
    0.88
     interpreter
    0.88
     surrogate
    0.86
    Act Density 0.081%

    No Known Activations