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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or strong opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating motivations or intentions, particularly regarding actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arbon
    -0.62
    anian
    -0.59
    greg
    -0.58
    anos
    -0.58
     Gujar
    -0.58
     menace
    -0.55
    igl
    -0.54
    famous
    -0.54
    ificial
    -0.54
    chip
    -0.54
    POSITIVE LOGITS
    antry
    0.56
     toward
    0.55
     earnest
    0.55
     bribes
    0.53
     motives
    0.53
     altru
    0.53
    ooter
    0.52
     sincere
    0.52
     diligence
    0.51
    esty
    0.50
    Act Density 1.130%

    No Known Activations