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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or states of being with a focus on emotional and social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REFERRED
    -0.16
    nga
    -0.15
    ajan
    -0.15
    ieux
    -0.15
    illance
    -0.14
    ONSE
    -0.14
    лаÑģ
    -0.14
    TRANSFER
    -0.14
     represented
    -0.14
     promises
    -0.14
    POSITIVE LOGITS
     NEGLIGENCE
    0.16
    ado
    0.15
     possess
    0.15
    ÏĢει
    0.15
     tent
    0.15
     Poss
    0.15
     messenger
    0.15
     trace
    0.14
    enia
    0.14
     possession
    0.14
    Act Density 0.014%

    No Known Activations