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

    Neuronpedia

    INDEX
    Explanations

    the word "favorites" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    коз
    -0.15
    žit
    -0.14
    aN
    -0.14
    066
    -0.14
    uale
    -0.14
    864
    -0.14
    ARA
    -0.14
     Sword
    -0.14
    ìĩ
    -0.14
    ara
    -0.13
    POSITIVE LOGITS
     Ngá»įc
    0.15
     Hud
    0.14
    .ico
    0.14
    åį
    0.14
    baru
    0.14
    微软éĽħé»ij
    0.13
    ÅĻad
    0.13
    _GPU
    0.13
     Tos
    0.13
     Mate
    0.13
    Act Density 0.001%

    No Known Activations