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

    Neuronpedia

    INDEX
    Explanations

    instances of the variable "val" in code snippets

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Bohr
    -0.74
    zee
    -0.72
     Pears
    -0.71
     Sahara
    -0.71
     Bohn
    -0.70
     ESE
    -0.70
     ASE
    -0.69
     emir
    -0.69
    gabe
    -0.68
    thalt
    -0.68
    POSITIVE LOGITS
     val
    1.09
     Val
    0.99
     Valky
    0.91
     Valdez
    0.90
    ConstraintMaker
    0.90
     VAL
    0.89
    val
    0.88
    Val
    0.85
     Valk
    0.84
    ])):
    0.84
    Act Density 0.017%

    No Known Activations