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

    Neuronpedia

    INDEX
    Explanations

    verbs related to deliberate actions performed with a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with actions and operations affecting systems or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tone
    -0.67
    conn
    -0.64
    zo
    -0.58
    gins
    -0.58
    eur
    -0.56
    SW
    -0.53
    اÙĦ
    -0.51
    ricks
    -0.51
    nex
    -0.51
    ele
    -0.50
    POSITIVE LOGITS
    ometimes
    1.02
    omething
    0.92
    hift
    0.89
    paces
    0.78
    ynthesis
    0.76
    ilver
    0.75
    hirt
    0.73
    heet
    0.73
    ettings
    0.69
    terness
    0.66
    Act Density 0.390%

    No Known Activations