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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "natural" and its variations, along with terms related to otherness or removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.59
    contentLoaded
    -0.59
    GEBURTSDATUM
    -0.58
    DIPSETTING
    -0.56
    pushFollow
    -0.54
     itſelf
    -0.52
    })->
    -0.49
     ujednoznacz
    -0.49
     negatives
    -0.49
    ANCIAL
    -0.49
    POSITIVE LOGITS
     Kal
    0.40
     <<<<<<<<<<<<<<
    0.38
    +:+
    0.33
    Véxase
    0.33
     Kam
    0.32
     schemes
    0.32
    под
    0.30
     lo
    0.30
     respe
    0.29
     particularly
    0.29
    Act Density 0.027%

    No Known Activations