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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating results or conclusions drawn from evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.56
    CloseOperation
    -0.43
    isalpha
    -0.42
    놨
    -0.42
     sarung
    -0.42
    
    -0.42
    zzleHttp
    -0.41
    getActiveSheet
    -0.40
    Tikang
    -0.39
    adeloupe
    -0.39
    POSITIVE LOGITS
     his
    0.96
     her
    0.83
     him
    0.82
    Their
    0.82
    their
    0.79
     their
    0.78
     Their
    0.78
     theſe
    0.77
     your
    0.77
     그녀
    0.75
    Act Density 3.981%

    No Known Activations