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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ongoing processes or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    好äºĨ
    -0.17
    ÏĦÏį
    -0.14
    ilio
    -0.14
    alse
    -0.14
     longtime
    -0.13
    onga
    -0.13
    Ïĥμο
    -0.13
    utt
    -0.13
     Podle
    -0.13
    obsolete
    -0.13
    POSITIVE LOGITS
     nas
    0.50
     fled
    0.41
     young
    0.38
     emerging
    0.35
     still
    0.34
     newly
    0.34
    nas
    0.33
     emerg
    0.33
     henüz
    0.32
    ãģ¾ãģł
    0.31
    Act Density 0.283%

    No Known Activations