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

    Neuronpedia

    INDEX
    Explanations

    references to programming parameters or configuration options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilder
    -0.15
    INVAL
    -0.14
    fect
    -0.14
    atz
    -0.14
    329
    -0.14
    fft
    -0.14
    ff
    -0.14
    Pod
    -0.14
    710
    -0.14
    steder
    -0.14
    POSITIVE LOGITS
    _yes
    0.25
     YES
    0.24
     yes
    0.23
    YES
    0.23
     Yes
    0.22
    yes
    0.21
     true
    0.19
    Yes
    0.19
    true
    0.19
    _YES
    0.18
    Act Density 0.161%

    No Known Activations