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

    Neuronpedia

    INDEX
    Explanations

    words related to acts of chopping or cutting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ch" within various contexts, indicating a focus on words that contain this specific character sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PORT
    -0.83
    gaard
    -0.76
    WARD
    -0.75
    ITED
    -0.74
    INGTON
    -0.74
    ENCE
    -0.73
    DragonMagazine
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.70
    berman
    -0.69
    glas
    -0.67
    POSITIVE LOGITS
    amps
    1.33
    icago
    1.13
    inese
    1.09
    ipper
    1.07
    ipping
    1.06
    aps
    1.05
    amp
    1.05
    ippers
    1.05
    akra
    1.04
    ipped
    1.04
    Act Density 0.016%

    No Known Activations