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

    Neuronpedia

    INDEX
    Explanations

    assertions or commands used in testing code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etting
    -0.17
    hide
    -0.16
    ouse
    -0.15
    aybe
    -0.15
    isle
    -0.15
    emics
    -0.15
    itters
    -0.15
    ihan
    -0.14
    aho
    -0.14
    lashes
    -0.14
    POSITIVE LOGITS
    ions
    0.26
    edly
    0.24
    IONS
    0.24
    ion
    0.21
    ION
    0.18
    ainty
    0.18
    ations
    0.17
    iveness
    0.17
    ional
    0.17
    ively
    0.17
    Act Density 0.008%

    No Known Activations