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

    Neuronpedia

    INDEX
    Explanations

    declarations of variable values in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    3
    -0.39
    puis
    -0.36
    bird
    -0.35
    Another
    -0.35
    another
    -0.35
    DoesNotExist
    -0.34
    house
    -0.34
     another
    -0.34
     Bör
    -0.34
     Schne
    -0.34
    POSITIVE LOGITS
     val
    1.98
    val
    1.95
     Val
    1.74
    Val
    1.73
     VAL
    1.70
    VAL
    1.69
     vals
    1.27
     Valerie
    1.27
     valer
    1.23
    Vals
    1.21
    Act Density 0.059%

    No Known Activations