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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and pronouns suggesting uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .userInteractionEnabled
    -0.15
    lou
    -0.15
    ileen
    -0.15
    nict
    -0.15
    Planning
    -0.14
    aran
    -0.14
    urga
    -0.14
    ongan
    -0.14
     اÙĦÙħد
    -0.14
    hled
    -0.14
    POSITIVE LOGITS
    responsive
    0.15
    antom
    0.15
    lead
    0.14
    represent
    0.14
    cha
    0.14
    iges
    0.14
     equ
    0.14
     interpre
    0.14
    ponsive
    0.14
    -contrib
    0.14
    Act Density 0.021%

    No Known Activations