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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something that is no longer present or valid

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĭãģªãģĦ
    -0.19
    essim
    -0.16
    .scalablytyped
    -0.14
    Ùħا
    -0.14
     Still
    -0.14
    MOTE
    -0.14
    awning
    -0.14
     prone
    -0.14
     заг
    -0.13
    adoo
    -0.13
    POSITIVE LOGITS
    oven
    0.16
     anymore
    0.15
    odzi
    0.14
    epad
    0.14
    _FMT
    0.14
     necessarily
    0.14
    overy
    0.14
    ÃŃc
    0.14
    iw
    0.14
    odian
    0.14
    Act Density 0.011%

    No Known Activations