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

    Neuronpedia

    INDEX
    Explanations

    the token "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    recurring high-frequency phrases or elements related to ongoing situations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.74
     frontline
    -0.72
     neighb
    -0.70
     receiving
    -0.69
     prosec
    -0.68
     regener
    -0.67
     labelled
    -0.66
     spir
    -0.66
     petrol
    -0.66
     scrap
    -0.66
    POSITIVE LOGITS
    Reviewer
    1.39
    Advertisements
    1.31
    Reviewed
    1.29
    Contents
    1.27
    Rated
    1.26
    Trivia
    1.20
    Posted
    1.18
    Whether
    1.16
    Enlarge
    1.16
    Offline
    1.16
    Act Density 0.449%

    No Known Activations