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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate support or endorsement of actions, initiatives, or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to support or endorsement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     cabinet
    -0.67
    hatt
    -0.67
    fty
    -0.64
    hern
    -0.62
     Zan
    -0.62
    sbm
    -0.62
     reluct
    -0.62
    reau
    -0.62
    adder
    -0.61
    iece
    -0.60
    POSITIVE LOGITS
     GMOs
    0.67
    auna
    0.65
     PHI
    0.65
     Brach
    0.64
     LW
    0.62
    izes
    0.61
     inflammation
    0.60
    ides
    0.60
    é¾įå¥ij士
    0.58
     copyrighted
    0.58
    Act Density 0.251%

    No Known Activations