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

    Neuronpedia

    INDEX
    Explanations

    indicators of programming or configuration settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olin
    -0.18
     hammer
    -0.16
     Canter
    -0.15
    /vnd
    -0.15
    wifi
    -0.15
    opher
    -0.15
    rani
    -0.15
    dens
    -0.14
     Hamm
    -0.14
    ften
    -0.14
    POSITIVE LOGITS
    icos
    0.15
    ipples
    0.14
    ociety
    0.14
    ÑĤаб
    0.14
    ennon
    0.14
    öh
    0.14
    (strpos
    0.14
     Ges
    0.13
    ergy
    0.13
    omens
    0.13
    Act Density 0.009%

    No Known Activations