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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating anticipation or expectation

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing anticipation or eagerness about future events or collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thinkable
    -0.68
    arton
    -0.68
    Cry
    -0.68
    taboola
    -0.65
    umes
    -0.65
    soDeliveryDate
    -0.63
    olitical
    -0.63
    intosh
    -0.62
    ey
    -0.62
    urance
    -0.61
    POSITIVE LOGITS
     seeing
    1.39
     hearing
    1.26
     welcoming
    1.18
     exploring
    1.07
     learning
    1.05
     continuing
    1.04
     collaborating
    1.03
     witnessing
    1.01
     interacting
    1.00
     sharing
    0.98
    Act Density 0.085%

    No Known Activations