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

    Neuronpedia

    INDEX
    Explanations

    special characters and non-English characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols in text, particularly those related to data formatting or database terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.04
     Jaw
    -0.57
     Jury
    -0.57
     symp
    -0.54
    NPR
    -0.53
     condos
    -0.52
    poll
    -0.52
    cuts
    -0.51
    :]
    -0.51
    zl
    -0.51
    POSITIVE LOGITS
    ioxide
    0.81
    Ö¼
    0.67
    bia
    0.64
    glers
    0.63
    owler
    0.63
    iland
    0.61
    Offset
    0.58
    swick
    0.55
    »Ĵ
    0.55
    ouple
    0.54
    Act Density 0.793%

    No Known Activations