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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a desire for further information or reading material

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    宾
    -0.16
    anford
    -0.15
    ariate
    -0.15
    ê°ģ
    -0.15
    åĻ
    -0.14
     Correspond
    -0.14
    벨
    -0.14
    ariat
    -0.14
     Wax
    -0.14
    Çİ
    -0.14
    POSITIVE LOGITS
    ameda
    0.19
    OWNER
    0.15
    /method
    0.15
     dul
    0.14
    wm
    0.14
     Damen
    0.13
    xa
    0.13
    conc
    0.13
    -striped
    0.13
    cope
    0.13
    Act Density 0.405%

    No Known Activations