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

    Neuronpedia

    INDEX
    Explanations

    statements or opinions expressed by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "saying" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.92
    visible
    -0.78
    peg
    -0.75
    ocument
    -0.73
    Poké
    -0.73
    \/\/
    -0.72
    gomery
    -0.70
    esc
    -0.70
    transfer
    -0.70
    èª
    -0.69
    POSITIVE LOGITS
     ISPs
    0.66
     they
    0.66
     it
    0.65
     goodbye
    0.64
     '[
    0.63
     apart
    0.61
     "[
    0.60
     abusers
    0.59
     constituents
    0.57
     Af
    0.57
    Act Density 0.076%

    No Known Activations