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

    Neuronpedia

    INDEX
    Explanations

    phrases related to job positions or roles

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used in various contexts or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombs
    -0.71
    POST
    -0.70
    ãĥ¥
    -0.69
    oras
    -0.68
    ople
    -0.67
    oes
    -0.67
    ron
    -0.66
    rax
    -0.66
    OUGH
    -0.65
     VIDEOS
    -0.64
    POSITIVE LOGITS
    pires
    1.13
    pired
    1.11
     well
    1.02
     opposed
    0.90
    piring
    0.86
    ynchron
    0.85
    bestos
    0.83
    phy
    0.81
     follows
    0.80
    pire
    0.78
    Act Density 0.189%

    No Known Activations