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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating evaluation or discussion of significant issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ois
    -0.14
    ounc
    -0.14
    غاÙĦ
    -0.13
    oth
    -0.13
    æĪĸèĢħ
    -0.12
    ixel
    -0.12
    6
    -0.12
    ec
    -0.11
    agg
    -0.11
    .vis
    -0.11
    POSITIVE LOGITS
    sched
    0.15
    ezi
    0.15
    aliz
    0.14
     why
    0.14
    eum
    0.14
    Occurrences
    0.14
    jedn
    0.14
    OutOfRangeException
    0.13
    -Semit
    0.13
     hereby
    0.13
    Act Density 0.040%

    No Known Activations