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

    Neuronpedia

    INDEX
    Explanations

    words related to the action of sneezing

    oai_token-act-pair · gpt-3.5-turbo

    words associated with stealthy or sneaky actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĩ
    -0.77
    imon
    -0.73
    falls
    -0.70
    NPR
    -0.70
    imately
    -0.67
    FORM
    -0.65
    Fed
    -0.65
    ento
    -0.63
    minus
    -0.61
     whales
    -0.61
    POSITIVE LOGITS
     Villa
    0.92
    ez
    0.91
    eers
    0.86
    ering
    0.84
    ety
    0.83
    er
    0.83
    ey
    0.82
    aked
    0.80
    aky
    0.79
    eting
    0.77
    Act Density 0.044%

    No Known Activations