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

    Neuronpedia

    INDEX
    Explanations

    terms related to comprehensive services and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @student
    -0.17
    tid
    -0.17
    ÏįÏĦε
    -0.15
    laus
    -0.15
    ¾ç¤º
    -0.15
    etc
    -0.14
    à¸Ļà¸Ļ
    -0.14
    å±ŀäºİ
    -0.14
    ¯ÃĤ
    -0.13
    deaux
    -0.13
    POSITIVE LOGITS
     ranging
    0.75
     ranged
    0.50
     range
    0.49
     ranges
    0.47
     starting
    0.42
    —from
    0.40
     Range
    0.39
     RANGE
    0.38
    -ranging
    0.37
    .range
    0.37
    Act Density 0.350%

    No Known Activations