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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty and anticipation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.57
     كمان
    -0.54
    unmodifiable
    -0.54
     Վերցված
    -0.53
    Catatan
    -0.53
    geen
    -0.52
     fool
    -0.51
    CONSIN
    -0.51
     photolibrary
    -0.49
     ogóle
    -0.49
    POSITIVE LOGITS
    ❋
    0.61
     exploration
    0.56
     Exploration
    0.56
     curiosity
    0.56
     unfold
    0.55
     unravel
    0.55
     Investig
    0.54
    Resol
    0.53
    explore
    0.53
    Exploration
    0.53
    Act Density 0.281%

    No Known Activations