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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rame
    -0.16
    Ñıж
    -0.15
    stdClass
    -0.15
    tro
    -0.14
    azo
    -0.14
    acket
    -0.14
    athers
    -0.14
    quette
    -0.13
    lia
    -0.13
    Ñĩем
    -0.13
    POSITIVE LOGITS
     happen
    0.81
     happens
    0.81
     happened
    0.78
     happening
    0.76
     Happ
    0.66
     aconte
    0.57
     happ
    0.57
     occur
    0.53
     occurs
    0.53
     ocur
    0.51
    Act Density 0.271%

    No Known Activations