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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Black" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ft
    -0.16
    yp
    -0.15
    ient
    -0.15
    å®Ĺ
    -0.15
    lla
    -0.15
    uls
    -0.14
    elta
    -0.14
    ellites
    -0.14
    tsky
    -0.14
     Sons
    -0.14
    POSITIVE LOGITS
    anche
    0.23
     Bl
    0.22
    anks
    0.21
    /bl
    0.19
    ippi
    0.19
    .Bl
    0.18
    éri
    0.17
    .bl
    0.17
     bl
    0.16
    ount
    0.16
    Act Density 0.017%

    No Known Activations