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

    Neuronpedia

    INDEX
    Explanations

    equality or comparison expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trainer
    -0.15
    rams
    -0.14
     Homeland
    -0.14
    arlo
    -0.14
     conform
    -0.14
    Charsets
    -0.13
    uga
    -0.13
     Alic
    -0.13
    pector
    -0.13
     Spect
    -0.13
    POSITIVE LOGITS
    ustos
    0.19
    æ®
    0.15
    ænd
    0.15
    è
    0.15
    ¼åIJĪ
    0.15
    argo
    0.14
    _PF
    0.14
     اÙĩ
    0.14
    ose
    0.14
    ziej
    0.14
    Act Density 0.000%

    No Known Activations