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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    conditional and situational phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     communism
    -0.61
     blacklist
    -0.59
    module
    -0.59
     tubing
    -0.58
     flaw
    -0.58
     Centauri
    -0.58
     moratorium
    -0.58
     unden
    -0.58
    prints
    -0.58
     Soy
    -0.55
    POSITIVE LOGITS
    20439
    0.83
     ones
    0.70
    FactoryReloaded
    0.67
    auld
    0.66
    outhern
    0.66
    affected
    0.64
    ostic
    0.64
    ãĤ¡
    0.62
    ebted
    0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.61
    Act Density 0.164%

    No Known Activations