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

    Neuronpedia

    INDEX
    Explanations

    terms related to theoretical concepts and conditions in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esModule
    -0.59
     étrangère
    -0.52
     viktigt
    -0.43
    voller
    -0.42
    mischer
    -0.42
    曖昧さ回避
    -0.41
     Personal
    -0.40
    发表于
    -0.40
     humaines
    -0.40
     personlig
    -0.40
    POSITIVE LOGITS
     الرياضيه
    0.47
    dige
    0.45
     связанные
    0.45
     commune
    0.44
     sportive
    0.44
     blonde
    0.43
    ändige
    0.42
     zewnętrzne
    0.42
    AndEndTag
    0.41
    tonode
    0.41
    Act Density 0.074%

    No Known Activations