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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and adjectives related to quality or moral judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sitesinde
    -0.14
    &T
    -0.13
    ients
    -0.13
    /XML
    -0.13
    bcm
    -0.13
    IDER
    -0.13
    izr
    -0.13
    <typeof
    -0.13
    ameda
    -0.12
     Hammond
    -0.12
    POSITIVE LOGITS
     meaning
    0.28
    meaning
    0.20
    ness
    0.20
     =
    0.20
     means
    0.20
     noun
    0.19
    noun
    0.19
     itself
    0.18
     refers
    0.17
    íķĺëĭ¤
    0.17
    Act Density 0.289%

    No Known Activations