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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal thoughts, actions, or experiences

    oai_token-act-pair · gpt-3.5-turbo

    collective expressions of intention or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raft
    -0.68
    rift
    -0.66
    ournal
    -0.66
    resa
    -0.64
    opolis
    -0.63
     Patt
    -0.61
    plings
    -0.59
     Cheong
    -0.58
     Prometheus
    -0.57
     Penguin
    -0.55
    POSITIVE LOGITS
     sorely
    0.93
     dearly
    0.72
     insiders
    0.68
     aspire
    0.67
    ģĸ
    0.65
     minds
    0.64
     behold
    0.63
    ¶ħ
    0.63
     ordinarily
    0.62
     wat
    0.62
    Act Density 0.233%

    No Known Activations