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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we," indicating a focus on collective actions or viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kov
    -0.15
    rese
    -0.14
    .initialize
    -0.14
     Shields
    -0.14
    ows
    -0.14
    allas
    -0.14
    воÑİ
    -0.14
    positor
    -0.13
    .respond
    -0.13
    commend
    -0.13
    POSITIVE LOGITS
    SED
    0.15
    igon
    0.15
    _DEPRECATED
    0.15
    arten
    0.15
     kontakte
    0.14
    ãĥ³ãĤ°
    0.14
    athe
    0.14
    swick
    0.14
    constitution
    0.14
    zych
    0.14
    Act Density 0.065%

    No Known Activations