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

    Neuronpedia

    INDEX
    Explanations

    phrases related to donation or financial support

    oai_token-act-pair · gpt-3.5-turbo

    prompts for interaction or engagement from the audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cel
    -0.61
     costly
    -0.50
     replen
    -0.50
    ual
    -0.50
     unus
    -0.50
    .–
    -0.49
     cure
    -0.48
     manual
    -0.48
    ®
    -0.48
     escal
    -0.48
    POSITIVE LOGITS
    ichick
    0.57
     Huss
    0.57
    yip
    0.57
     Leban
    0.57
    idth
    0.57
     Beir
    0.56
    swick
    0.56
     namely
    0.56
    lain
    0.55
    midt
    0.54
    Act Density 0.963%

    No Known Activations