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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty or lack of knowledge

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.69
     RAD
    -0.68
     Shib
    -0.65
     guiActiveUnfocused
    -0.65
     Circus
    -0.64
     slug
    -0.64
     Sard
    -0.63
     assemb
    -0.62
     spiral
    -0.62
     Samar
    -0.61
    POSITIVE LOGITS
    yet
    0.98
    £
    0.93
    ¦
    0.87
    ¿
    0.87
    Ĭ
    0.85
    İ
    0.84
    ľ
    0.84
    Ĵ
    0.84
    quite
    0.82
    \'
    0.82
    Act Density 0.127%

    No Known Activations