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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of proximity or presence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "nowhere" and its variations, indicating a focus on lack of presence or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULT
    -0.74
    CVE
    -0.71
    ivation
    -0.65
     Reef
    -0.62
    ilt
    -0.61
    tein
    -0.59
    tl
    -0.58
    isations
    -0.57
    FA
    -0.57
    ultural
    -0.57
    POSITIVE LOGITS
     else
    1.21
    Else
    0.97
     Else
    0.95
    xus
    0.91
    upon
    0.85
    ¿½
    0.78
    abouts
    0.75
    else
    0.75
    ĸļ
    0.74
    ĪĴ
    0.71
    Act Density 0.017%

    No Known Activations