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

    Neuronpedia

    INDEX
    Explanations

    instances of expressions related to advice or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.75
     calendriers
    -0.73
    Datuak
    -0.64
    PYX
    -0.62
     ModelExpression
    -0.62
     Савезне
    -0.61
    +#+#
    -0.61
    Portail
    -0.57
    THISDAY
    -0.56
    Predecesor
    -0.56
    POSITIVE LOGITS
     There
    0.58
     When
    0.56
    There
    0.54
    When
    0.53
     If
    0.53
    ANTLR
    0.51
     there
    0.50
    tığı
    0.49
     The
    0.47
    If
    0.46
    Act Density 0.319%

    No Known Activations