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

    Neuronpedia

    INDEX
    Explanations

    numerical rankings and orderings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IED
    -0.15
    -suite
    -0.15
    htub
    -0.15
    åIJĪåIJĮ
    -0.14
    marsh
    -0.14
    Examples
    -0.14
    ARRIER
    -0.14
    ÑĨез
    -0.13
    ITES
    -0.13
    Numbers
    -0.13
    POSITIVE LOGITS
     two
    0.20
    -two
    0.20
    0.18
    -one
    0.18
     spot
    0.17
    -No
    0.17
     reason
    0.17
     three
    0.16
    iw
    0.15
    -three
    0.15
    Act Density 0.011%

    No Known Activations