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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal beliefs or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinion or belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.63
    ankind
    -0.61
     Written
    -0.60
    Ü
    -0.60
    abi
    -0.59
    begin
    -0.58
    guard
    -0.58
    mentioned
    -0.57
    lite
    -0.57
    beam
    -0.57
    POSITIVE LOGITS
    iewicz
    0.72
    olate
    0.71
    olated
    0.67
     passionately
    0.61
     himself
    0.60
    terson
    0.60
    aspers
    0.59
     Tues
    0.56
    phas
    0.56
    ajor
    0.55
    Act Density 0.188%

    No Known Activations