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

    Neuronpedia

    INDEX
    Explanations

    terms related to property or attribute definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =yes
    -0.19
    berman
    -0.16
    StateException
    -0.16
    =true
    -0.15
    =True
    -0.15
    imits
    -0.15
    berger
    -0.14
    =zeros
    -0.14
     Blo
    -0.14
    ouch
    -0.14
    POSITIVE LOGITS
    pattern
    0.30
    Pattern
    0.28
    -pattern
    0.26
     pattern
    0.26
     Pattern
    0.26
    patterns
    0.24
    _pattern
    0.24
    Patterns
    0.24
     Patterns
    0.21
     patterns
    0.21
    Act Density 0.207%

    No Known Activations