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

    Neuronpedia

    INDEX
    Explanations

    sentences that convey information, often starting with a statement about a person or situation

    oai_token-act-pair · gpt-3.5-turbo

    key pronouns and related speech patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ä
    -0.69
     CT
    -0.63
     �
    -0.63
     virgin
    -0.61
     liqu
    -0.60
     -->
    -0.60
     gener
    -0.58
     |--
    -0.57
     fry
    -0.57
     reversible
    -0.56
    POSITIVE LOGITS
    iannopoulos
    0.96
    vertisement
    0.95
    enhagen
    0.84
    mosp
    0.83
    lez
    0.81
    PDATE
    0.80
    oola
    0.77
    swers
    0.77
    aples
    0.76
     teasp
    0.74
    Act Density 0.393%

    No Known Activations