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

    Neuronpedia

    INDEX
    Explanations

    predictions or estimations about future outcomes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cession
    -0.73
    ppo
    -0.62
    noticed
    -0.61
    kay
    -0.59
    orget
    -0.59
    ateurs
    -0.58
    rosse
    -0.58
    estern
    -0.58
    merce
    -0.57
    ipop
    -0.56
    POSITIVE LOGITS
     to
    0.90
    to
    0.74
     likely
    0.71
    iant
    0.67
     capable
    0.66
    ivalent
    0.66
     destined
    0.65
     Cosponsors
    0.61
    ELF
    0.60
     TO
    0.60
    Act Density 0.348%

    No Known Activations