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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing emotional reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotional reactions and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brief
    -0.63
     indist
    -0.60
     gradual
    -0.60
    uly
    -0.59
    equ
    -0.59
    escal
    -0.58
     freely
    -0.58
    few
    -0.57
    arser
    -0.57
    annis
    -0.57
    POSITIVE LOGITS
     indeed
    0.68
    ––
    0.68
     considering
    0.67
    hyde
    0.65
    ãĤ¬
    0.64
    ktop
    0.64
    rez
    0.62
    mercial
    0.62
    Ùĩ
    0.62
     insofar
    0.62
    Act Density 0.400%

    No Known Activations