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

    Neuronpedia

    INDEX
    Explanations

    phrases related to skepticism and critical questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WAR
    -0.15
    ateau
    -0.14
    ustos
    -0.14
    ucid
    -0.14
    ½Ķ
    -0.14
    .Ret
    -0.14
    ête
    -0.14
    ÏĥÏĦÏģο
    -0.14
     ÙĪص
    -0.14
    ording
    -0.14
    POSITIVE LOGITS
     cop
    0.18
    orum
    0.15
     Miss
    0.15
    955
    0.15
    655
    0.15
    .fs
    0.15
     cont
    0.15
    jax
    0.15
     Cop
    0.14
     Undefined
    0.14
    Act Density 0.012%

    No Known Activations