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

    Neuronpedia

    INDEX
    Explanations

    references to radiators and related components in a mechanical or technical context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lia
    -0.59
    laus
    -0.59
    liness
    -0.58
    lins
    -0.57
    spin
    -0.56
    lish
    -0.56
    ledged
    -0.55
    fully
    -0.55
    mint
    -0.55
    theless
    -0.55
    POSITIVE LOGITS
    apers
    0.58
    otropic
    0.57
    orescence
    0.57
    ative
    0.56
    rogen
    0.56
    estate
    0.54
    ples
    0.54
    ologically
    0.52
    agen
    0.52
    aeda
    0.52
    Act Density 6.977%

    No Known Activations