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

    Neuronpedia

    INDEX
    Explanations

    verb phrases indicating speech or statements made by individuals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Theſe
    -0.92
    ^(@)
    -0.91
     Majefty
    -0.90
     tartalomajánló
    -0.88
    refour
    -0.84
     Anſ
    -0.83
     Efq
    -0.83
     Diſ
    -0.83
     ſtate
    -0.83
     purpoſe
    -0.83
    POSITIVE LOGITS
    Portail
    0.64
    ,
    0.52
     and
    0.52
     (
    0.51
    日
    0.50
     I
    0.43
    ↵↵
    0.43
    وله
    0.42
     
    0.41
     "
    0.41
    Act Density 0.004%

    No Known Activations