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

    Neuronpedia

    INDEX
    Explanations

    words related to medical treatments or procedures involving insertion or removal

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letters "ch" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PORT
    -0.87
    WARD
    -0.76
    ENCE
    -0.74
    gaard
    -0.74
    ITED
    -0.72
    DragonMagazine
    -0.70
    glas
    -0.69
    ERC
    -0.69
    INGTON
    -0.68
    FORMATION
    -0.66
    POSITIVE LOGITS
    amps
    1.25
    icago
    1.13
    ipper
    1.12
    inese
    1.08
    ippers
    1.08
    okers
    1.07
    aps
    1.05
    ipping
    1.05
    ipped
    1.04
    umps
    1.04
    Act Density 0.011%

    No Known Activations