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

    Neuronpedia

    INDEX
    Explanations

    words related to admiration or praise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kok
    -0.15
    uali
    -0.15
     Apex
    -0.15
    apel
    -0.15
    ectors
    -0.14
    icle
    -0.14
    acci
    -0.14
    gil
    -0.14
     Millennium
    -0.14
    ulation
    -0.14
    POSITIVE LOGITS
     Jad
    0.15
    .CG
    0.15
    ombat
    0.14
     Ud
    0.14
    unas
    0.14
    âĢ³E
    0.14
    Wunused
    0.14
    ingham
    0.14
     san
    0.14
     Intr
    0.14
    Act Density 0.059%

    No Known Activations