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

    Neuronpedia

    INDEX
    Explanations

    statements expressing personal thoughts, feelings, or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.71
     Benth
    -0.68
    zeera
    -0.63
    UnusedPrivate
    -0.63
    udios
    -0.61
     betweenstory
    -0.60
    fromnode
    -0.59
    atika
    -0.57
     dedans
    -0.56
     Litu
    -0.56
    POSITIVE LOGITS
     But
    0.88
     but
    0.85
    but
    0.84
    但她
    0.81
     pero
    0.78
     BUT
    0.77
    But
    0.77
     AssemblyVersion
    0.76
    BUT
    0.74
     definitely
    0.72
    Act Density 0.190%

    No Known Activations