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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating a lack of awareness or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.56
    astify
    -0.56
     ffilm
    -0.52
    CrossRef
    -0.50
     femininos
    -0.50
     femininas
    -0.49
    transQ
    -0.49
    OrBuilder
    -0.48
     nakalista
    -0.47
    Билгалдахарш
    -0.47
    POSITIVE LOGITS
     unaware
    0.69
     oblivious
    0.59
     unknowingly
    0.52
     ignorance
    0.51
     unwittingly
    0.46
     Ignorance
    0.45
     clueless
    0.45
     unsuspecting
    0.43
     ignorant
    0.43
    不知
    0.42
    Act Density 0.459%

    No Known Activations