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

    Neuronpedia

    INDEX
    Explanations

    negative contractions and words indicating limitation or inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vô
    -0.17
    ichert
    -0.16
    arie
    -0.16
    edii
    -0.15
     indirectly
    -0.15
     hâl
    -0.14
    _closure
    -0.14
    oodoo
    -0.13
    reet
    -0.13
    adh
    -0.13
    POSITIVE LOGITS
     miss
    0.29
     soon
    0.25
    miss
    0.25
     tire
    0.23
     Soon
    0.22
     misses
    0.21
     missed
    0.21
     disappoint
    0.20
     ever
    0.20
     resist
    0.20
    Act Density 0.093%

    No Known Activations