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

    Neuronpedia

    INDEX
    Explanations

    keywords related to different types of transitions or conversions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to varying forms of communication and societal influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QUI
    -0.61
    ullivan
    -0.58
    BUT
    -0.57
    relation
    -0.55
    UF
    -0.55
    Else
    -0.54
    é¾įåĸļ士
    -0.53
    Reloaded
    -0.52
    oster
    -0.52
    GC
    -0.51
    POSITIVE LOGITS
     onwards
    1.35
     onward
    1.31
     to
    1.14
     downwards
    0.95
     into
    0.92
     standpoint
    0.90
    to
    0.83
     onto
    0.82
     beginnings
    0.78
     unto
    0.76
    Act Density 0.396%

    No Known Activations