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

    Neuronpedia

    INDEX
    Explanations

    long sequences of dashes or underscores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tocin
    -0.78
     fees
    -0.76
    gok
    -0.76
     Ulysses
    -0.75
    ########.
    -0.74
     Hancock
    -0.73
     Waugh
    -0.73
     Suzy
    -0.73
     Skyl
    -0.73
    θρώ
    -0.72
    POSITIVE LOGITS
                            
    1.52
    1.21
                             
    1.07
    ="#"><
    0.91
                              
    0.91
     DPM
    0.88
    Lili
    0.82
    rd
    0.82
     ABCD
    0.82
     Lili
    0.81
    Act Density 0.046%

    No Known Activations