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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating remaining in a specific place or position

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to being dependent or remaining close to parents or guardians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.76
    çīĪ
    -0.61
    ELL
    -0.61
    omen
    -0.61
    è¦ļéĨĴ
    -0.61
     soph
    -0.60
    ISM
    -0.58
    properties
    -0.57
     inferred
    -0.57
    estic
    -0.56
    POSITIVE LOGITS
     indefinitely
    0.80
    andestine
    0.76
    lishes
    0.75
    hook
    0.74
     forever
    0.70
    shore
    0.70
    inse
    0.67
    leep
    0.67
     footing
    0.65
    erential
    0.64
    Act Density 0.092%

    No Known Activations