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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a state of being or existence, often expressing likelihood or observation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rones
    -0.71
     Rapids
    -0.65
     Earthqu
    -0.64
    alez
    -0.64
    theless
    -0.64
    rouse
    -0.64
    etime
    -0.62
     Mund
    -0.62
    anwhile
    -0.62
    otiation
    -0.61
    POSITIVE LOGITS
    fit
    0.80
    fits
    0.77
    Done
    0.76
    leeve
    0.75
    ono
    0.72
     done
    0.70
    league
    0.70
    ibe
    0.69
     progressing
    0.69
    ique
    0.68
    Act Density 0.055%

    No Known Activations