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

    Neuronpedia

    INDEX
    Explanations

    opinions or perspectives on various subjects

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to perceptions and judgments about individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.85
    sonian
    -0.84
     teasp
    -0.75
    isode
    -0.73
    aptic
    -0.71
    oult
    -0.69
    âĹ¼
    -0.69
    vic
    -0.68
    worth
    -0.67
     confir
    -0.67
    POSITIVE LOGITS
     themselves
    1.26
     himself
    1.15
     ourselves
    1.14
    phas
    1.14
     herself
    1.12
     oneself
    1.05
     them
    1.04
     homosexuality
    1.03
     itself
    1.02
     yourselves
    1.01
    Act Density 0.225%

    No Known Activations