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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    \/\/
    -0.82
     marg
    -0.71
     rejection
    -0.67
     affirmation
    -0.67
     contingency
    -0.66
     squee
    -0.66
     commitments
    -0.65
    chall
    -0.64
     persuasion
    -0.64
     mosqu
    -0.63
    POSITIVE LOGITS
    grade
    0.80
    oven
    0.76
    jiang
    0.73
    furt
    0.70
    gate
    0.68
    vern
    0.67
    Forge
    0.67
    ifted
    0.66
    llular
    0.66
    anguages
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.