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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating checks, searches, or evaluations for specific outcomes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ì¶ĺ
    -0.15
    KeyType
    -0.15
    oton
    -0.15
     yük
    -0.15
    vertis
    -0.15
     Heap
    -0.14
    ndern
    -0.14
    antine
    -0.14
    agara
    -0.14
    /kernel
    -0.13
    POSITIVE LOGITS
     any
    0.20
     ANY
    0.16
     Patterns
    0.15
    ÑıÑĩ
    0.15
     patterns
    0.15
     Any
    0.15
    .any
    0.15
    any
    0.15
    -any
    0.15
     pattern
    0.15
    Act Density 0.164%

    No Known Activations