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

    Neuronpedia

    INDEX
    Explanations

    phrases related to aspirations or fears

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope and fear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eni
    -0.72
    elta
    -0.70
    akia
    -0.59
    redd
    -0.59
    TPPStreamerBot
    -0.59
    iery
    -0.58
    nia
    -0.58
    ivot
    -0.57
    nova
    -0.56
    vision
    -0.56
    POSITIVE LOGITS
     they
    0.98
     that
    0.90
     THEY
    0.86
     thereof
    0.85
     lest
    0.84
     of
    0.80
     nobody
    0.73
    they
    0.69
     it
    0.69
    that
    0.68
    Act Density 0.088%

    No Known Activations