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

    Neuronpedia

    INDEX
    Explanations

    references to legal or official matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or decisions related to legal and governmental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     realise
    -0.74
     civilisation
    -0.71
     Whilst
    -0.71
    )!
    -0.71
    !".
    -0.70
    Firstly
    -0.68
    !'
    -0.66
    '.
    -0.65
     GREAT
    -0.64
     whilst
    -0.63
    POSITIVE LOGITS
     "'
    0.69
     unspecified
    0.66
     unauthorized
    0.62
     improperly
    0.58
     unidentified
    0.58
     customized
    0.54
     redacted
    0.54
     disputed
    0.54
     canceled
    0.54
     plaintiffs
    0.53
    Act Density 1.432%

    No Known Activations