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

    Neuronpedia

    INDEX
    Explanations

    topics or subjects that authors have written extensively about

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating academic or scholarly work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ographers
    -0.73
    pite
    -0.73
    ographer
    -0.71
    ":[
    -0.71
    quez
    -0.66
    ï¸ı
    -0.64
    vous
    -0.64
    fax
    -0.64
    DERR
    -0.64
    OUR
    -0.63
    POSITIVE LOGITS
     topics
    1.03
     behalf
    1.01
     how
    0.85
     comparative
    0.83
     combating
    0.83
     UFOs
    0.83
     psychology
    0.82
     sexuality
    0.81
     homosexuality
    0.80
     why
    0.79
    Act Density 0.251%

    No Known Activations