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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate intention or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the purpose or intent behind actions or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.73
    anon
    -0.70
    Pass
    -0.67
     Solitaire
    -0.67
    lv
    -0.66
     Combine
    -0.65
     Leilan
    -0.65
    natureconservancy
    -0.64
    Optional
    -0.64
     Rampage
    -0.63
    POSITIVE LOGITS
    ovie
    0.97
    sonian
    0.96
     toward
    0.93
    yrinth
    0.88
     squarely
    0.88
     aimed
    0.87
     towards
    0.83
    irection
    0.82
    ggle
    0.77
     aiming
    0.76
    Act Density 0.023%

    No Known Activations