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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ventures
    -0.65
    impact
    -0.64
    Mind
    -0.63
    venture
    -0.60
     categor
    -0.60
     DPRK
    -0.60
     impacts
    -0.59
    minster
    -0.59
     reperc
    -0.58
     affirmative
    -0.58
    POSITIVE LOGITS
    leaf
    0.76
    iring
    0.71
    iste
    0.71
    ITCH
    0.70
    adoes
    0.69
    reet
    0.66
     correction
    0.66
    ignment
    0.66
    ookie
    0.66
    aa
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.