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

    Neuronpedia

    INDEX
    Explanations

    statements that indicate whether something is logical or understandable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gesteld
    -0.66
    tagHelper
    -0.63
     Albion
    -0.63
     betreft
    -0.60
     ospiti
    -0.57
    cèse
    -0.56
    ={`/
    -0.55
     lifestyles
    -0.54
     بث
    -0.54
     occasions
    -0.53
    POSITIVE LOGITS
     nonsense
    0.81
    nonsense
    0.81
    Nonsense
    0.80
    ensical
    0.76
    coher
    0.67
     logique
    0.65
    onsense
    0.64
     gibber
    0.63
     logical
    0.62
     sensible
    0.60
    Act Density 0.171%

    No Known Activations