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

    Neuronpedia

    INDEX
    Explanations

    statements addressing the severity of problematic scenarios or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ABCDEFGHI
    -0.15
    RunWith
    -0.15
    alom
    -0.15
    cobra
    -0.14
    oad
    -0.14
    uars
    -0.14
    aser
    -0.14
    AMA
    -0.14
    amburger
    -0.13
    fur
    -0.13
    POSITIVE LOGITS
     kind
    0.40
     type
    0.36
     kinds
    0.35
    -type
    0.29
     exact
    0.29
    type
    0.28
    kind
    0.28
     sorts
    0.27
     sort
    0.27
     types
    0.25
    Act Density 0.174%

    No Known Activations