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

    Neuronpedia

    INDEX
    Explanations

    JavaScript function names and operations like 'insert', 'fetch', and 'update'

    oai_token-act-pair · gpt-3.5-turbo

    references to user-related functions or actions within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĶ°
    -0.79
     disg
    -0.77
    taboola
    -0.77
     fabrication
    -0.73
     prosecut
    -0.72
     unavoid
    -0.70
    theless
    -0.69
     challeng
    -0.67
     apologies
    -0.66
     interchange
    -0.65
    POSITIVE LOGITS
    ()
    1.26
    ())
    1.21
    ();
    1.20
    ().
    1.18
    (),
    1.14
    ());
    1.09
    ():
    1.07
    ById
    1.06
    (_
    1.06
    Item
    1.02
    Act Density 0.058%

    No Known Activations