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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking actions that have a strong potential impact

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with outcomes or consequences of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quart
    -0.77
    advertisement
    -0.61
     supposed
    -0.60
    pmwiki
    -0.59
     lately
    -0.59
     experimented
    -0.59
     observes
    -0.58
    Pic
    -0.57
     Doesn
    -0.57
    numbered
    -0.57
    POSITIVE LOGITS
    enance
    0.78
    uate
    0.77
    ELY
    0.75
    glers
    0.71
    ificantly
    0.70
    ãĥķãĤ©
    0.69
    orage
    0.68
    geries
    0.68
     significantly
    0.67
     considerably
    0.67
    Act Density 0.308%

    No Known Activations