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

    Neuronpedia

    INDEX
    Explanations

    words related to trademarks or products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to academic positions or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRD
    -0.74
     DRAG
    -0.70
     srfAttach
    -0.66
    galitarian
    -0.66
    isSpecialOrderable
    -0.66
     Tunis
    -0.65
    OE
    -0.64
     mosqu
    -0.62
    abwe
    -0.62
    ESH
    -0.61
    POSITIVE LOGITS
    ures
    1.04
    ure
    0.93
    heid
    0.87
    ions
    0.85
    icularly
    0.83
    umbn
    0.82
    s
    0.77
    rontal
    0.76
    baugh
    0.74
    cil
    0.74
    Act Density 0.087%

    No Known Activations