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

    Neuronpedia

    INDEX
    Explanations

    phrases related to small measurements or amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to proportions and fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OWS
    -0.76
    TOP
    -0.70
    ãĤ¹ãĥĪ
    -0.68
    ãĤ¤ãĥĪ
    -0.68
    Reviewer
    -0.67
    Ãį
    -0.66
    Trend
    -0.66
    ennes
    -0.65
    uments
    -0.64
    çİĭ
    -0.64
    POSITIVE LOGITS
    dozen
    0.98
     dozen
    0.97
    icum
    0.89
     (~
    0.82
    omething
    0.82
     (<
    0.81
    nown
    0.75
    abyte
    0.75
     tolerated
    0.74
     kilomet
    0.72
    Act Density 0.433%

    No Known Activations