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

    Neuronpedia

    INDEX
    Explanations

    instructions or technical specifications for configuring and using electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erest
    -0.76
    enhagen
    -0.66
    itiveness
    -0.65
    terday
    -0.64
    reprene
    -0.59
     uproar
    -0.57
    sonian
    -0.57
     unlaw
    -0.56
    efe
    -0.55
    aster
    -0.55
    POSITIVE LOGITS
     opposed
    1.29
    ynchron
    1.27
     follows
    1.09
     shown
    1.07
    semble
    1.05
     described
    1.04
    pect
    0.95
    ynchronous
    0.95
     indicated
    0.92
    well
    0.92
    Act Density 0.099%

    No Known Activations