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

    Neuronpedia

    INDEX
    Explanations

    phrases that signify relationships or associations, particularly those involving the terms "as" and "for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arkin
    -0.16
    bor
    -0.16
    reon
    -0.15
    ooter
    -0.15
    gesi
    -0.15
    ër
    -0.14
    εÏį
    -0.14
     Camb
    -0.14
    stantiateViewController
    -0.14
    .bd
    -0.14
    POSITIVE LOGITS
    andes
    0.17
    rix
    0.15
    osos
    0.15
    isser
    0.14
    uten
    0.14
    ìĬ¤ì½Ķ
    0.14
    appen
    0.14
     retire
    0.14
    /gin
    0.14
    itter
    0.14
    Act Density 0.299%

    No Known Activations