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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and specialized terms in various fields

    oai_token-act-pair · gpt-3.5-turbo

    words associated with significant or impactful actions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     showc
    -0.70
     defamation
    -0.63
     dispatch
    -0.62
     foul
    -0.60
     libel
    -0.60
    assetsadobe
    -0.60
    etheless
    -0.59
     steering
    -0.59
     armed
    -0.58
     icing
    -0.58
    POSITIVE LOGITS
    idae
    0.75
    Norm
    0.73
     Nights
    0.72
    odon
    0.71
    aceae
    0.70
     Series
    0.70
    opter
    0.69
     Definition
    0.68
    Effects
    0.66
     Spaces
    0.66
    Act Density 0.444%

    No Known Activations