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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and requirements

    oai_token-act-pair · gpt-3.5-turbo

    references to specifications and requirements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reon
    -0.77
    redo
    -0.68
    ievers
    -0.67
     oun
    -0.67
    ollah
    -0.64
     someday
    -0.63
     commuting
    -0.62
     destro
    -0.60
    eren
    -0.60
     fantas
    -0.60
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.21
    ====
    1.13
    :-
    1.12
    --------
    1.11
    ============
    1.09
    ========
    1.09
    ----------
    1.07
    ----------------
    1.03
    ------------------------------------------------
    0.99
    --------------------------------
    0.96
    Act Density 0.157%

    No Known Activations