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

    Neuronpedia

    INDEX
    Explanations

    links to external websites or resources that provide additional information on a topic

    oai_token-act-pair · gpt-3.5-turbo

    links or references to external resources or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rek
    -0.75
    ģĸ
    -0.73
    acters
    -0.68
     premiered
    -0.67
     Nightmares
    -0.66
    estro
    -0.65
     hatched
    -0.64
    yu
    -0.63
     Maver
    -0.62
     Anarchy
    -0.61
    POSITIVE LOGITS
     accuser
    0.69
    lihood
    0.66
     Attribution
    0.66
    ifter
    0.64
    ollah
    0.64
    Marginal
    0.64
    hibit
    0.64
    igslist
    0.63
    look
    0.63
     accus
    0.63
    Act Density 0.000%

    No Known Activations