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

    Neuronpedia

    INDEX
    Explanations

    words that express necessity or desire for action and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ureau
    -0.17
    ãĥ³ãĥĶ
    -0.17
    acob
    -0.15
    rief
    -0.15
    γγ
    -0.15
    ãĥĨãĥ«
    -0.15
    estone
    -0.14
    warnings
    -0.14
     tel
    -0.14
    caster
    -0.13
    POSITIVE LOGITS
     Pai
    0.16
    ey
    0.15
    ye
    0.15
    ily
    0.14
    -regexp
    0.14
    vens
    0.14
    ilia
    0.14
    ÙĪÙĨد
    0.14
    _UPPER
    0.14
    vore
    0.14
    Act Density 0.001%

    No Known Activations