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

    Neuronpedia

    INDEX
    Explanations

    verbs that involve decision-making or taking action

    oai_token-act-pair · gpt-3.5-turbo

    actions related to movement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eka
    -0.62
    ère
    -0.58
    iere
    -0.58
    vu
    -0.55
    si
    -0.52
    eq
    -0.52
     Aerospace
    -0.52
    udos
    -0.50
    ega
    -0.50
     Jol
    -0.50
    POSITIVE LOGITS
    redients
    0.74
    tons
    0.66
     oneself
    0.60
    HAM
    0.59
     suspic
    0.58
     IPM
    0.56
     exha
    0.55
     torches
    0.54
     hearts
    0.52
    AME
    0.52
    Act Density 0.645%

    No Known Activations