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

    Neuronpedia

    INDEX
    Explanations

    words related to defects or issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to defects or deficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fare
    -0.78
    76561
    -0.73
    iland
    -0.73
    eter
    -0.67
    apest
    -0.66
    stead
    -0.66
    ahon
    -0.64
    ffield
    -0.64
    elcome
    -0.63
    dress
    -0.63
    POSITIVE LOGITS
    ions
    0.89
    icient
    0.85
    ively
    0.80
    inia
    0.77
    rees
    0.77
    acies
    0.76
    ioned
    0.74
    ion
    0.72
    orius
    0.72
    escent
    0.71
    Act Density 0.067%

    No Known Activations