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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms associated with acceptability or standards

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

    acceptable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.40
     tours
    -0.36
     read
    -0.35
     tour
    -0.35
     crow
    -0.35
     Ferri
    -0.35
    writing
    -0.35
    mortar
    -0.34
     in
    -0.34
     trus
    -0.33
    POSITIVE LOGITS
     acceptable
    2.03
     Acceptable
    1.89
    Acceptable
    1.86
    acceptable
    1.85
     unacceptable
    1.46
    ceptable
    1.36
     acceptability
    1.32
    accep
    1.14
     tolerable
    1.09
     accep
    1.09
    Act Density 0.009%

    No Known Activations