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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and public affairs

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conditional scenarios or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ey
    -0.59
    ety
    -0.58
    atorium
    -0.58
     Anniversary
    -0.57
     Stard
    -0.56
     Helm
    -0.53
     Maid
    -0.53
     Hearth
    -0.51
     Joh
    -0.50
     Tropical
    -0.49
    POSITIVE LOGITS
     thereby
    0.84
    entimes
    0.73
    particularly
    0.68
    etheless
    0.68
     preferably
    0.67
    nown
    0.67
    rather
    0.65
    especially
    0.64
     namely
    0.63
    instead
    0.62
    Act Density 0.943%

    No Known Activations