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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and their usage in conjunction with negations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Appears after "male" and "female"

    np_acts-logits-general · gemini-2.0-flash

    male and female

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.54
     defaultstate
    -0.52
    SourceChecksum
    -0.51
     Normdatei
    -0.50
    Rptr
    -0.49
     Grüsse
    -0.46
    gehende
    -0.45
    gründ
    -0.45
     nahilalakip
    -0.45
     utilising
    -0.45
    POSITIVE LOGITS
    LookAnd
    0.43
    ])))
    0.40
     Prince
    0.39
     prince
    0.39
     middle
    0.39
     *
    0.39
     FontWeight
    0.39
     and
    0.39
     brown
    0.39
     Chriftian
    0.38
    Act Density 0.804%

    No Known Activations