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

    Neuronpedia

    INDEX
    Explanations

    phrases related to employment and hiring practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rum
    -0.18
    ash
    -0.16
    ruc
    -0.16
    amac
    -0.16
    unma
    -0.15
    /he
    -0.15
    anker
    -0.15
    Throw
    -0.15
    ely
    -0.15
    cem
    -0.14
    POSITIVE LOGITS
    ean
    0.18
    ysz
    0.16
    /lic
    0.15
    hold
    0.15
    iske
    0.14
    holds
    0.14
    ments
    0.14
    ½Ķ
    0.14
    ees
    0.14
    iculty
    0.14
    Act Density 0.023%

    No Known Activations