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

    Neuronpedia

    INDEX
    Explanations

    the infinitive form of verbs, particularly those indicating actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loff
    -0.17
    åĨĮ
    -0.16
    urator
    -0.14
    mons
    -0.14
    lation
    -0.14
    cken
    -0.13
     Opposition
    -0.13
    ocab
    -0.13
    tres
    -0.13
    Advisor
    -0.13
    POSITIVE LOGITS
    empo
    0.16
     Lives
    0.16
    lut
    0.15
    erner
    0.15
    ornings
    0.15
    565
    0.15
    hower
    0.14
    zzle
    0.14
    LD
    0.14
    _MPI
    0.14
    Act Density 0.013%

    No Known Activations