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

    Neuronpedia

    INDEX
    Explanations

    names of individuals in leadership or managerial roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑĮ
    -0.17
    /tiny
    -0.16
    agina
    -0.15
    dda
    -0.15
    enties
    -0.14
    οκ
    -0.14
    dd
    -0.14
    bv
    -0.14
     startup
    -0.14
    fluid
    -0.13
    POSITIVE LOGITS
     himself
    0.19
    olars
    0.18
    sembled
    0.17
    JNI
    0.15
    COMPARE
    0.15
    chet
    0.15
    loth
    0.14
    Thickness
    0.14
    odash
    0.14
    ione
    0.14
    Act Density 0.142%

    No Known Activations