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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a direct confrontation or interaction with someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "face."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©Ł
    -0.79
    ary
    -0.72
    icultural
    -0.69
    chy
    -0.66
    imer
    -0.66
    rom
    -0.65
    isl
    -0.64
    isol
    -0.64
    ucky
    -0.60
    amber
    -0.60
    POSITIVE LOGITS
     face
    1.10
     faces
    0.99
    face
    0.91
    liest
    0.86
    crow
    0.85
     Faces
    0.83
    faced
    0.83
    nings
    0.83
    Face
    0.82
    breakers
    0.80
    Act Density 0.026%

    No Known Activations