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

    Neuronpedia

    INDEX
    Explanations

    expressions related to being "out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TCR
    -0.72
    etheless
    -0.71
     صوتيه
    -0.68
    ized
    -0.67
    enya
    -0.66
    quelize
    -0.63
    nology
    -0.63
    ed
    -0.63
    initComponents
    -0.63
    varande
    -0.62
    POSITIVE LOGITS
     OUT
    1.30
     Out
    1.17
     out
    1.16
    Out
    1.11
    out
    1.08
    OUT
    0.94
    getOut
    0.93
     outs
    0.92
     []:
    0.87
    EOUT
    0.78
    Act Density 0.134%

    No Known Activations