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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or likelihood combined with specific verbs

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating speculation or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reloaded
    -0.76
     Beats
    -0.62
    vasive
    -0.60
     Bird
    -0.60
     Glob
    -0.60
    Enough
    -0.59
    Rat
    -0.58
    enthal
    -0.58
    aroo
    -0.57
    BuyableInstoreAndOnline
    -0.57
    POSITIVE LOGITS
     notice
    1.26
     wonder
    1.25
     remember
    1.20
     recall
    1.14
     recognise
    1.14
     want
    1.12
     wanna
    1.11
     wondering
    1.10
     recognize
    1.09
     ask
    1.08
    Act Density 0.099%

    No Known Activations