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

    Neuronpedia

    INDEX
    Explanations

    concepts related to negative and positive affirmations and the impact of language on thoughts and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ythe
    -0.16
    yre
    -0.15
    iddi
    -0.13
    oon
    -0.13
     èŃ
    -0.13
    .tool
    -0.13
    -generic
    -0.13
    sr
    -0.13
     Writers
    -0.13
     deduct
    -0.13
    POSITIVE LOGITS
     utter
    0.42
    utter
    0.37
     rec
    0.31
     say
    0.30
     Ut
    0.30
     saying
    0.29
     ut
    0.28
    utters
    0.28
     said
    0.27
     uttered
    0.27
    Act Density 0.312%

    No Known Activations