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

    Neuronpedia

    INDEX
    Explanations

    adjectives or verbs related to significant impactful events or actions

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating significant actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hump
    -0.70
     Gors
    -0.65
     Dome
    -0.62
     Meridian
    -0.57
     buys
    -0.56
    PI
    -0.55
     syndrome
    -0.55
     nig
    -0.55
     contracted
    -0.55
     Stur
    -0.54
    POSITIVE LOGITS
    Ĥİ
    0.92
    ¿½
    0.78
    eatures
    0.75
    ĺħ
    0.74
    ŃĶ
    0.73
    FML
    0.73
    ĸļ
    0.73
    ESCO
    0.72
    acters
    0.72
     partName
    0.70
    Act Density 0.437%

    No Known Activations