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

    Neuronpedia

    INDEX
    Explanations

    names of people or characters associated with historical or fictional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aille
    -0.16
    yd
    -0.16
     Jacqu
    -0.16
    VERT
    -0.15
    hood
    -0.15
    FFFFFFFF
    -0.15
    ffffffff
    -0.15
    hots
    -0.14
    rede
    -0.14
    .sd
    -0.14
    POSITIVE LOGITS
    zen
    0.55
    ze
    0.54
    zer
    0.49
    z
    0.48
    zes
    0.45
    za
    0.44
    zs
    0.43
    zt
    0.42
    zi
    0.41
    zo
    0.41
    Act Density 0.038%

    No Known Activations