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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific types or qualities, such as "the type of," "the kind of," "the sort of," or "the model that."

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing types or kinds of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zar
    -0.74
    issions
    -0.70
    usions
    -0.69
     SQ
    -0.64
    arie
    -0.64
     JJ
    -0.64
    INAL
    -0.63
     COUR
    -0.62
    arts
    -0.62
    lations
    -0.61
    POSITIVE LOGITS
    yip
    0.94
     nightmares
    0.74
     afforded
    0.73
    76561
    0.71
     ordinarily
    0.66
    veyard
    0.62
     Limbaugh
    0.62
    uman
    0.61
     nightmare
    0.61
     normally
    0.60
    Act Density 0.112%

    No Known Activations