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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases indicating completion or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditions and qualifications in a process or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toggle
    -0.78
    fter
    -0.76
    picture
    -0.67
    guide
    -0.67
     LOT
    -0.64
     Shots
    -0.63
    ][/
    -0.62
    photo
    -0.60
    ggles
    -0.60
    gery
    -0.60
    POSITIVE LOGITS
     raining
    1.01
     interven
    0.68
    unes
    0.66
     ratified
    0.65
     costs
    0.65
    rodu
    0.65
     impossible
    0.64
     predecessor
    0.63
     reopened
    0.62
     itself
    0.62
    Act Density 0.639%

    No Known Activations