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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "continue"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "continue" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usterity
    -0.78
    ranch
    -0.77
    aster
    -0.76
    acho
    -0.74
    */(
    -0.71
    ramid
    -0.71
    lier
    -0.70
    ixed
    -0.70
    oster
    -0.70
    essee
    -0.70
    POSITIVE LOGITS
     uninterrupted
    0.82
     unab
    0.82
     indefinitely
    0.77
     ende
    0.75
     progressing
    0.73
     unanswered
    0.73
     unchanged
    0.69
     onward
    0.67
    noon
    0.65
     afloat
    0.64
    Act Density 0.037%

    No Known Activations