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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ulative
    -0.76
    APH
    -0.75
    phrine
    -0.73
    stro
    -0.71
    ium
    -0.68
    iami
    -0.68
     horizont
    -0.68
    iam
    -0.67
    dated
    -0.65
    staking
    -0.64
    POSITIVE LOGITS
    GBT
    0.72
    ï¸ı
    0.63
     GOODMAN
    0.63
     Krishna
    0.62
    λ
    0.62
    raq
    0.61
    oppable
    0.61
    ç«
    0.61
    pec
    0.61
    åij
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.