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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proper nouns, particularly names of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific term or acronym that is likely to be related to organizations or companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.83
     compuls
    -0.75
    perate
    -0.70
     differe
    -0.70
    ve
    -0.69
    nery
    -0.67
     Catalyst
    -0.67
    vez
    -0.67
     quo
    -0.67
    taboola
    -0.65
    POSITIVE LOGITS
    onent
    1.30
    odcast
    1.24
    olitan
    1.05
    ortun
    1.01
    owered
    0.99
    ensable
    0.98
    oulos
    0.94
    ressor
    0.91
    endium
    0.91
    ractical
    0.91
    Act Density 0.025%

    No Known Activations