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

    Neuronpedia

    INDEX
    Explanations

    terms and expressions related to assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efon
    -0.15
    olt
    -0.15
    lk
    -0.15
    efs
    -0.15
    Gas
    -0.14
    eki
    -0.14
    аÑĢам
    -0.14
    rift
    -0.14
    lope
    -0.14
    inos
    -0.14
    POSITIVE LOGITS
     Schul
    0.15
     loose
    0.14
     credits
    0.14
     Corner
    0.14
     corners
    0.14
    bon
    0.14
     pais
    0.14
    /pass
    0.14
     kot
    0.13
    787
    0.13
    Act Density 0.021%

    No Known Activations