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

    Neuronpedia

    INDEX
    Explanations

    references to follow-up actions or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ToolTip
    -0.16
    اض
    -0.15
    ninger
    -0.15
    uts
    -0.14
    iete
    -0.14
    Äįky
    -0.14
    ieten
    -0.14
    ubi
    -0.14
    uli
    -0.13
    à¸Ļำ
    -0.13
    POSITIVE LOGITS
     follow
    0.34
     Follow
    0.31
    Follow
    0.29
    .follow
    0.28
    follow
    0.27
    -follow
    0.25
    _follow
    0.21
     follows
    0.20
    -up
    0.19
     FOLLOW
    0.19
    Act Density 0.007%

    No Known Activations