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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eeee
    -0.78
     Rebell
    -0.68
    Feel
    -0.65
    Gender
    -0.64
    ivas
    -0.64
    eous
    -0.64
    enne
    -0.63
    Reply
    -0.63
     COUR
    -0.63
    leness
    -0.63
    POSITIVE LOGITS
    pired
    1.04
    phy
    0.99
     opposed
    0.96
     well
    0.94
    pects
    0.90
    part
    0.90
    piring
    0.89
    ynchron
    0.89
     soon
    0.89
    pires
    0.85
    Act Density 0.213%

    No Known Activations