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

    Neuronpedia

    INDEX
    Explanations

    words related to evaluation or measurement

    oai_token-act-pair · gpt-3.5-turbo

    references to authority or significant individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.73
    hig
    -0.69
    .–
    -0.69
    .):
    -0.65
    Interstitial
    -0.64
    onew
    -0.61
    Cause
    -0.61
    ilaterally
    -0.60
    nova
    -0.59
    $.
    -0.58
    POSITIVE LOGITS
     they
    0.92
     we
    0.90
    yip
    0.86
     he
    0.85
     THEY
    0.85
    soever
    0.85
     thou
    0.84
     she
    0.75
     you
    0.72
    they
    0.70
    Act Density 0.255%

    No Known Activations