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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize quantities or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.74
    .
    -0.74
     in
    -0.68
    ;
    -0.67
    ModelForm
    -0.67
    JAXB
    -0.58
     Berman
    -0.57
     (~(
    -0.56
     Berger
    -0.55
    :
    -0.55
    POSITIVE LOGITS
    Aiheesta
    1.04
    ^(@)
    0.90
     ſeveral
    0.88
     plufieurs
    0.87
    NegativeButton
    0.84
     Efq
    0.82
     Monfieur
    0.81
    Cuánt
    0.80
     aéri
    0.80
     fewer
    0.79
    Act Density 0.213%

    No Known Activations