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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or operations, particularly verbs describing work or movement

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and participles related to various forms of activity or work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombat
    -0.71
    uckle
    -0.71
    ont
    -0.70
    oxy
    -0.70
    ilet
    -0.68
    ana
    -0.66
    chini
    -0.66
    peg
    -0.66
    anya
    -0.65
    ochond
    -0.65
    POSITIVE LOGITS
    edIn
    0.68
     conduc
    0.61
     fictitious
    0.60
     Muss
    0.60
    tons
    0.59
     theirs
    0.58
    rily
    0.58
     rall
    0.57
     Towards
    0.57
     peril
    0.56
    Act Density 0.280%

    No Known Activations