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

    Neuronpedia

    INDEX
    Explanations

    references to small sizes or scales

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     size
    -0.78
     Sizing
    -0.78
     itſelf
    -0.76
     sizing
    -0.76
     SIZE
    -0.72
     sizes
    -0.71
    numerusform
    -0.70
     Jeffries
    -0.70
     sized
    -0.69
    Климат
    -0.69
    POSITIVE LOGITS
    __*/
    0.77
     nahilalakip
    0.74
     distract
    0.71
    pausal
    0.69
    omethyl
    0.65
     Courant
    0.64
    reditation
    0.63
     roh
    0.63
    s
    0.63
     Chantal
    0.63
    Act Density 0.045%

    No Known Activations