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

    Neuronpedia

    INDEX
    Explanations

    programming or coding-related terms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     =
    -0.18
    anded
    -0.16
    ugh
    -0.15
    iap
    -0.15
     sobie
    -0.15
    æ
    -0.14
    ghost
    -0.14
    Diamond
    -0.14
    aps
    -0.14
    _unref
    -0.14
    POSITIVE LOGITS
     respondsToSelector
    0.15
    .alloc
    0.15
     Latter
    0.15
    utan
    0.14
    (@"
    0.14
    allo
    0.14
     perform
    0.14
     Bucc
    0.14
     alloc
    0.14
    memberOf
    0.14
    Act Density 0.009%

    No Known Activations