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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or sections in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.76
    mergeFrom
    -0.72
    DIPSETTING
    -0.70
    unknownFields
    -0.67
    rrggbb
    -0.67
    StoryboardSegue
    -0.66
    UserScript
    -0.66
    .’”
    -0.66
    });*/
    -0.65
     Efq
    -0.63
    POSITIVE LOGITS
     paire
    0.57
    ot
    0.56
    φέ
    0.52
    上面
    0.51
     impli
    0.51
     toit
    0.51
     produt
    0.50
    OMES
    0.50
    ct
    0.50
    telse
    0.49
    Act Density 0.811%

    No Known Activations