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

    Neuronpedia

    INDEX
    Explanations

    words related to elements of data tutorial systems

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "es" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.91
     Cruiser
    -0.73
    ISM
    -0.69
    ãĥ£
    -0.68
    >>\
    -0.65
    horse
    -0.64
     Carnage
    -0.63
     Unle
    -0.63
    ALLY
    -0.63
    ============
    -0.62
    POSITIVE LOGITS
    terday
    0.97
    uits
    0.90
    cul
    0.90
    gard
    0.86
    ktop
    0.86
    lev
    0.83
    ports
    0.83
    pect
    0.82
    earch
    0.82
    por
    0.82
    Act Density 0.072%

    No Known Activations