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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events that require anticipation or hope

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voting and civic engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    missible
    -0.68
    tein
    -0.68
    etheless
    -0.63
    atton
    -0.57
     deport
    -0.57
     persistent
    -0.56
    struct
    -0.55
    ophon
    -0.55
    gewater
    -0.55
     spons
    -0.54
    POSITIVE LOGITS
    iest
    0.81
     counterparts
    0.70
     selves
    0.67
    atonin
    0.67
     brethren
    0.66
     wisely
    0.66
     outdoors
    0.66
    favorite
    0.65
    elfth
    0.63
     credentials
    0.63
    Act Density 0.295%

    No Known Activations