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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recent events or announcements

    oai_token-act-pair · gpt-3.5-turbo

    present tense verbs indicating possession or availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.76
    seless
    -0.72
    ecd
    -0.68
    abuse
    -0.67
    externalActionCode
    -0.61
     harms
    -0.60
    Enlarge
    -0.60
    ails
    -0.59
    âĻ¦
    -0.59
    fail
    -0.58
    POSITIVE LOGITS
     teamed
    1.46
     partnered
    1.28
     been
    1.27
     begun
    1.22
     collaborated
    1.16
     embarked
    1.14
     decided
    1.11
     gotten
    1.09
     chosen
    1.08
     assembled
    1.05
    Act Density 0.243%

    No Known Activations