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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'S' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     برانيه
    -1.13
     ſeveral
    -0.92
     ―――――
    -0.86
     ſever
    -0.84
     Anſ
    -0.82
     themſelves
    -0.80
     viſ
    -0.80
     Monfieur
    -0.79
     pleaſure
    -0.79
     Diſ
    -0.79
    POSITIVE LOGITS
     S
    2.91
    S
    2.45
     getS
    1.91
     s
    1.83
    getS
    1.76
    cS
    1.45
    𝑆
    1.37
    Ｓ
    1.32
    mS
    1.31
    dS
    1.30
    Act Density 0.144%

    No Known Activations