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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical details and specifications

    oai_token-act-pair · gpt-3.5-turbo

    instances of copyright or ownership statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shove
    -0.69
     manif
    -0.64
     decon
    -0.61
     scissors
    -0.60
     prest
    -0.59
    ccess
    -0.58
     standing
    -0.57
     casc
    -0.57
    wagen
    -0.57
    milo
    -0.56
    POSITIVE LOGITS
     Advertisement
    0.87
    =-=-=-=-=-=-=-=-
    0.82
    =-=-=-=-
    0.78
    webkit
    0.73
    RAM
    0.71
    immune
    0.69
    HOU
    0.69
    taboola
    0.69
    Fish
    0.67
    lore
    0.66
    Act Density 0.023%

    No Known Activations