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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing particularity or specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by a reason or condition

    np_acts-logits-general · gemini-2.0-flash

    especially or particularly with specific condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.78
     EconPapers
    -0.71
    mbic
    -0.67
    tagHelperRunner
    -0.67
     himſelf
    -0.66
    $_['
    -0.66
    DebuggerNonUser
    -0.62
    MessageOf
    -0.62
     poffible
    -0.62
    rrggbb
    -0.61
    POSITIVE LOGITS
     when
    0.86
     if
    0.85
     during
    0.78
     in
    0.77
     those
    0.72
     especially
    0.72
     after
    0.68
     without
    0.67
     for
    0.67
     at
    0.66
    Act Density 0.166%

    No Known Activations