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

    Neuronpedia

    INDEX
    Explanations

    phrases related to online interactions and engagements

    oai_token-act-pair · gpt-3.5-turbo

    actions related to user interactions or engagements, particularly in online contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shine
    -0.60
    egal
    -0.58
    velt
    -0.58
    anz
    -0.56
    rans
    -0.55
     Palestin
    -0.54
     pronounced
    -0.53
    elin
    -0.53
     reconstructed
    -0.52
     consolidation
    -0.52
    POSITIVE LOGITS
    taboola
    0.87
    wheel
    0.71
     guiActive
    0.71
    thumbnails
    0.66
     Cancel
    0.65
    assis
    0.65
    otton
    0.65
    river
    0.65
    animous
    0.64
    rect
    0.63
    Act Density 0.019%

    No Known Activations