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

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal and social matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramids
    -0.86
    abella
    -0.79
     Regions
    -0.77
    docs
    -0.76
    upt
    -0.74
    ricanes
    -0.74
    »Ĵ
    -0.73
    undreds
    -0.71
    apeake
    -0.70
    姫
    -0.70
    POSITIVE LOGITS
     akin
    0.98
     nonetheless
    0.91
     worthy
    0.90
     rather
    0.89
     unworthy
    0.86
     deserving
    0.85
     requiring
    0.85
     worth
    0.82
     punishable
    0.82
     unto
    0.81
    Act Density 0.161%

    No Known Activations