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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of specific time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADC
    -0.18
    çĵľ
    -0.16
     Eh
    -0.15
    ãĥ¼ãĥ©
    -0.15
    ader
    -0.15
    idd
    -0.15
    bx
    -0.15
     ADC
    -0.14
    odef
    -0.14
    ิà¹Ģศษ
    -0.14
    POSITIVE LOGITS
    453
    0.16
    izedName
    0.15
    ÏĥÏĦαν
    0.15
    egl
    0.15
    osed
    0.15
    227
    0.15
    esty
    0.15
    627
    0.14
    shed
    0.14
    iese
    0.14
    Act Density 0.178%

    No Known Activations