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

    Neuronpedia

    INDEX
    Explanations

    the concept of familiarity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.17
    yu
    -0.16
    il
    -0.16
    gun
    -0.15
    eding
    -0.15
    hton
    -0.14
     Witness
    -0.14
    uesta
    -0.14
    /man
    -0.14
    efeller
    -0.14
    POSITIVE LOGITS
    ly
    0.23
    æĤī
    0.22
    mente
    0.21
    ably
    0.18
    ize
    0.16
    fare
    0.16
     ground
    0.16
     enough
    0.15
    encing
    0.15
    izable
    0.14
    Act Density 0.021%

    No Known Activations