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

    Neuronpedia

    INDEX
    Explanations

    instances of reluctance or hesitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enz
    -0.15
    epar
    -0.15
    ancell
    -0.15
     Kre
    -0.14
    WISE
    -0.14
     Wand
    -0.14
    vero
    -0.14
    utations
    -0.14
    iske
    -0.14
    pii
    -0.14
    POSITIVE LOGITS
     nor
    0.45
    nor
    0.35
    Nor
    0.33
     Nor
    0.32
     NOR
    0.24
     anymore
    0.24
     Norris
    0.21
     sondern
    0.19
     ani
    0.19
     بÙĦÚ©Ùĩ
    0.19
    Act Density 0.282%

    No Known Activations