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

    Neuronpedia

    INDEX
    Explanations

    verbs describing actions or states that are done to something

    oai_token-act-pair · gpt-3.5-turbo

    past participles of verbs, indicating actions or states that have been completed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alos
    -0.99
    ©¶æ
    -0.87
    someone
    -0.80
    vertisement
    -0.78
    ĪĴ
    -0.78
    athy
    -0.77
     teasp
    -0.77
    osponsors
    -0.74
    alon
    -0.71
    adra
    -0.70
    POSITIVE LOGITS
     commodity
    0.70
     notions
    0.64
     (<
    0.64
     fact
    0.63
     facts
    0.62
     (>
    0.62
     but
    0.61
     demographic
    0.61
     friendships
    0.60
     examples
    0.60
    Act Density 0.200%

    No Known Activations