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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating propositions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.87
     Normdatei
    -0.86
     BorderRadius
    -0.84
     Malk
    -0.82
     immemorial
    -0.80
    nloa
    -0.78
    STEIN
    -0.76
    böz
    -0.74
    Wal
    -0.74
     Eliz
    -0.74
    POSITIVE LOGITS
     SUGGEST
    1.18
     suggestions
    1.17
    ugges
    1.12
     suggested
    1.11
    SUGGEST
    1.09
    Suggestions
    1.08
     Suggestions
    1.07
    suggestions
    1.06
     suggest
    1.05
    Suggest
    1.04
    Act Density 0.106%

    No Known Activations