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

    Neuronpedia

    INDEX
    Explanations

    uncertainty or lack of clarity in text passages

    oai_token-act-pair · gpt-3.5-turbo

    inquiries or questions about unspecified details or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orned
    -0.69
    scan
    -0.68
    Ń·
    -0.67
    cery
    -0.66
    por
    -0.65
    iege
    -0.64
    ourn
    -0.64
    anova
    -0.63
    emp
    -0.63
    ffiti
    -0.63
    POSITIVE LOGITS
     constitutes
    1.29
     happens
    1.28
     happened
    1.20
     kinds
    1.18
     transpired
    1.16
     kind
    1.15
     sort
    1.09
     motiv
    1.08
     percentage
    1.06
     extent
    1.05
    Act Density 0.094%

    No Known Activations