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

    Neuronpedia

    INDEX
    Explanations

    instances of code-related terminology and variable manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }:=\
    -0.45
     papilla
    -0.44
    Và
    -0.44
     Alejandro
    -0.43
    ibles
    -0.42
    ÁND
    -0.42
    STRUCTOR
    -0.41
    Còn
    -0.41
     Mue
    -0.41
     Leer
    -0.41
    POSITIVE LOGITS
    Tikang
    0.58
    inha
    0.58
    Vidite
    0.55
    inhos
    0.54
    ões
    0.52
    inhas
    0.52
     виправивши
    0.51
    irão
    0.49
    inho
    0.49
    ô
    0.48
    Act Density 0.069%

    No Known Activations