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

    Neuronpedia

    INDEX
    Explanations

    references to callback functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tiary
    -0.51
     Katherine
    -0.47
    tete
    -0.46
    ttal
    -0.45
    tungen
    -0.45
    óra
    -0.45
     deepcopy
    -0.45
    webkit
    -0.43
    nava
    -0.43
    mmation
    -0.43
    POSITIVE LOGITS
     lean
    1.14
     leaning
    0.91
     leans
    0.90
    consensus
    0.90
     CURIAM
    0.88
    mybatisplus
    0.86
     Harris
    0.85
     Consensus
    0.84
     leaned
    0.84
     Lean
    0.84
    Act Density 0.081%

    No Known Activations