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

    Neuronpedia

    INDEX
    Explanations

    phrases related to understanding or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge, understanding, or awareness of a situation or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    robe
    -0.71
    ji
    -0.70
    udi
    -0.69
    inence
    -0.69
     Sabha
    -0.68
    owsky
    -0.67
    luster
    -0.66
    swick
    -0.65
    eln
    -0.64
    erate
    -0.64
    POSITIVE LOGITS
     happened
    0.84
     happ
    0.84
     happens
    0.79
     transpired
    0.78
     kinds
    0.74
     else
    0.73
     kind
    0.70
    Terror
    0.69
     awaits
    0.68
     Pax
    0.67
    Act Density 0.081%

    No Known Activations