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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate rejection or disapproval

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.76
    ố
    -0.66
     Din
    -0.65
    Hv
    -0.63
    двига
    -0.61
     Baile
    -0.60
     Duff
    -0.60
     oblig
    -0.58
    huff
    -0.58
     Dien
    -0.57
    POSITIVE LOGITS
     reject
    1.38
     Rejection
    1.33
     Reject
    1.32
     rejection
    1.28
    Rejection
    1.20
     rejected
    1.19
     rejects
    1.16
    rejected
    1.16
    Reject
    1.14
     rejecting
    1.13
    Act Density 0.012%

    No Known Activations