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

    Neuronpedia

    INDEX
    Explanations

    clarifications or affirmations in statements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     artificiales
    -0.50
     piped
    -0.49
     plă
    -0.48
     GenerationType
    -0.47
     çev
    -0.46
     educativas
    -0.46
     căr
    -0.46
    せっかく
    -0.46
    transQ
    -0.46
     însă
    -0.45
    POSITIVE LOGITS
    abinieri
    0.68
     تضيفلها
    0.68
    MigrationBuilder
    0.66
    zzleHttp
    0.64
    expandindo
    0.63
    qrstuvwxyz
    0.59
    arques
    0.58
    openzeppelin
    0.58
    protoimpl
    0.57
    arschu
    0.57
    Act Density 0.052%

    No Known Activations