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

    Neuronpedia

    INDEX
    Explanations

    specific details within sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote details or specifics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ools
    -0.70
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.70
    ione
    -0.69
    Creat
    -0.68
    Cath
    -0.67
    archy
    -0.66
    masters
    -0.65
    aline
    -0.64
    sters
    -0.64
    ONSORED
    -0.63
    POSITIVE LOGITS
     specifics
    0.82
     particulars
    0.79
     details
    0.78
     redacted
    0.71
     detail
    0.70
    £ı
    0.69
     whereabouts
    0.67
     nuances
    0.67
     transpired
    0.66
     backstory
    0.66
    Act Density 0.143%

    No Known Activations