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

    Neuronpedia

    INDEX
    Explanations

    words related to revealing or sharing information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the disclosure of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ichick
    -0.77
    uve
    -0.76
    ively
    -0.75
    igue
    -0.72
    ouf
    -0.72
    ENDED
    -0.70
    helm
    -0.67
    imore
    -0.64
    hammad
    -0.63
    ingu
    -0.63
    POSITIVE LOGITS
    IGH
    0.84
    TAIN
    0.83
    doms
    0.75
    hiba
    0.70
    stood
    0.69
    tesy
    0.68
    vern
    0.67
    ysis
    0.66
     divul
    0.65
    Letter
    0.65
    Act Density 0.042%

    No Known Activations