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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and control flow structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    2
    -0.21
    3
    -0.20
    1
    -0.18
    4
    -0.18
    *,
    -0.18
    5
    -0.17
    8
    -0.16
    9
    -0.15
    #,
    -0.14
    u
    -0.14
    POSITIVE LOGITS
     hasattr
    0.40
     isinstance
    0.38
     len
    0.32
    (isinstance
    0.31
    (len
    0.28
     any
    0.28
     not
    0.24
     callable
    0.23
    (has
    0.23
     ':'
    0.22
    Act Density 0.014%

    No Known Activations