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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the inclusion of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "includes" and its variations indicating lists or content details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pal
    -0.65
     astron
    -0.65
     rise
    -0.63
    osta
    -0.62
    iet
    -0.62
    rait
    -0.62
    ggles
    -0.61
    acia
    -0.61
    arc
    -0.61
     ascend
    -0.61
    POSITIVE LOGITS
    ometimes
    0.76
     prominently
    0.76
    :-
    0.75
     Include
    0.73
     INCLUD
    0.71
    ãĤ´
    0.70
    minus
    0.70
    :#
    0.69
    anamo
    0.69
    :'
    0.68
    Act Density 0.025%

    No Known Activations