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

    Neuronpedia

    INDEX
    Explanations

    phrases urging or inviting someone to do something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "come" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthodox
    -0.79
    visors
    -0.75
    popular
    -0.71
    ruff
    -0.70
    orsi
    -0.70
    hedon
    -0.70
    rating
    -0.69
    osterone
    -0.69
    rated
    -0.68
    uliffe
    -0.67
    POSITIVE LOGITS
     hither
    1.10
    backs
    0.98
    upp
    0.81
     forth
    0.78
    leon
    0.76
     WRITE
    0.73
     true
    0.68
     Morning
    0.68
    back
    0.66
     pouring
    0.66
    Act Density 0.042%

    No Known Activations