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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and publication details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     linkovi
    -0.75
    oredCriteria
    -0.74
     '\\;'
    -0.72
    InitVars
    -0.70
    lapsingToolbar
    -0.68
     noDo
    -0.68
    anskje
    -0.67
     conmigo
    -0.66
    يكب
    -0.65
    يميديا
    -0.63
    POSITIVE LOGITS
     The
    0.45
    SPATH
    0.43
    antd
    0.43
    amer
    0.42
     transformer
    0.42
    htë
    0.41
    The
    0.40
    localctx
    0.40
    Monte
    0.39
    Pfalz
    0.39
    Act Density 0.095%

    No Known Activations