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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions occurring after a main event

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "afterward" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    foot
    -0.74
    jah
    -0.70
    yu
    -0.69
    rod
    -0.68
    footed
    -0.65
    aez
    -0.63
    enberg
    -0.61
    headed
    -0.61
    eu
    -0.61
    hy
    -0.60
    POSITIVE LOGITS
    etheless
    0.81
    eatures
    0.78
     conclud
    0.78
    gradation
    0.75
    aneously
    0.73
    vernment
    0.73
    noon
    0.72
     afterwards
    0.71
    IRE
    0.71
    theless
    0.69
    Act Density 0.009%

    No Known Activations