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

    Neuronpedia

    INDEX
    Explanations

    project or initiative descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to various "about" sections or key terms related to projects and topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.83
    reviewed
    -0.73
    room
    -0.71
    cil
    -0.69
    ngth
    -0.67
    ias
    -0.65
    mony
    -0.65
    bender
    -0.65
     Boyle
    -0.63
    oft
    -0.63
    POSITIVE LOGITS
     nipple
    0.73
    oneliness
    0.71
     daddy
    0.69
     impending
    0.67
     nipples
    0.65
     vacations
    0.64
     Kardash
    0.63
     disappearing
    0.63
     holidays
    0.63
     allergies
    0.63
    Act Density 0.205%

    No Known Activations