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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or questioning of reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MBProgressHUD
    -0.15
    odus
    -0.15
    bject
    -0.15
    ä¹ħ
    -0.14
    icina
    -0.14
    ibal
    -0.14
    ìĻĦ
    -0.14
    KHR
    -0.14
    665
    -0.13
    OTO
    -0.13
    POSITIVE LOGITS
     happen
    0.94
     happened
    0.93
     happens
    0.91
     happening
    0.88
     Happ
    0.80
     happ
    0.70
     aconte
    0.67
    åıijçĶŁ
    0.63
     occurred
    0.57
     occur
    0.56
    Act Density 0.377%

    No Known Activations