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

    Neuronpedia

    INDEX
    Explanations

    assertive phrases indicating strong belief or conviction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong conviction or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hang
    -0.68
    orig
    -0.65
    umble
    -0.64
    checks
    -0.63
    flow
    -0.61
    mage
    -0.61
    Ye
    -0.60
    rawl
    -0.60
    VERTISEMENT
    -0.59
    ggles
    -0.59
    POSITIVE LOGITS
     enough
    0.88
    enough
    0.71
    ulously
    0.70
    rists
    0.70
    quartered
    0.68
    FN
    0.65
     nonetheless
    0.65
    terday
    0.64
    lly
    0.63
    ļé
    0.63
    Act Density 0.142%

    No Known Activations