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

    Neuronpedia

    INDEX
    Explanations

    quotations and statements made by various individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of direct speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oros
    -0.68
    oin
    -0.60
    atible
    -0.59
    irie
    -0.58
    isi
    -0.57
     Covenant
    -0.56
    earable
    -0.56
    resa
    -0.55
    ensible
    -0.55
    geist
    -0.55
    POSITIVE LOGITS
     adding
    1.35
     referring
    1.29
     noting
    1.18
     citing
    1.16
     recalling
    1.14
     emphasizing
    1.13
     stressing
    1.11
     echoing
    1.08
     quoting
    1.07
     referencing
    1.06
    Act Density 0.130%

    No Known Activations