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

    Neuronpedia

    INDEX
    Explanations

    capital letters or acronyms

    oai_token-act-pair · gpt-3.5-turbo

    references to various organizations or groups, particularly their initials or acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.81
    terday
    -0.66
     profiling
    -0.65
     unison
    -0.63
     provoking
    -0.63
     spirited
    -0.63
     haste
    -0.63
     teasing
    -0.62
    edIn
    -0.61
     juggling
    -0.61
    POSITIVE LOGITS
    RC
    1.09
    CCC
    1.04
    FP
    1.02
    GC
    1.02
    SC
    1.00
    PD
    0.99
    CS
    0.99
    PP
    0.98
    DF
    0.98
    CC
    0.95
    Act Density 0.175%

    No Known Activations