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

    Neuronpedia

    INDEX
    Explanations

    mentions of events happening in a particular format or location

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to stand-up comedy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.69
     Rica
    -0.65
    jri
    -0.64
     constitu
    -0.64
    tera
    -0.61
    ãģ®éŃĶ
    -0.60
    achev
    -0.59
    isconsin
    -0.59
    theless
    -0.58
    myra
    -0.57
    POSITIVE LOGITS
    alone
    0.98
    through
    0.98
    bys
    0.91
    up
    0.91
    around
    0.89
    gap
    0.87
    holders
    0.87
    offs
    0.86
    upon
    0.86
    oop
    0.85
    Act Density 0.042%

    No Known Activations