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

    Neuronpedia

    INDEX
    Explanations

    information related to news reporting or coverage

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the preposition "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YE
    -0.97
    ©¶æ¥µ
    -0.94
    few
    -0.90
    SourceFile
    -0.90
    STEM
    -0.74
    FML
    -0.74
    externalActionCode
    -0.71
    NK
    -0.69
    949
    -0.69
    YP
    -0.69
    POSITIVE LOGITS
     behalf
    1.40
    erous
    1.07
    shore
    0.89
    etime
    0.83
     occasion
    0.79
    eness
    0.76
     Sundays
    0.75
    yx
    0.74
     topics
    0.72
     Saturdays
    0.72
    Act Density 0.103%

    No Known Activations