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

    Neuronpedia

    INDEX
    Explanations

    random sequences of characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "K"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itism
    -0.84
    ĸļ
    -0.82
    ppelin
    -0.77
    ality
    -0.76
    ourced
    -0.76
    ourcing
    -0.75
    hips
    -0.75
    iday
    -0.75
    omnia
    -0.74
    iflower
    -0.73
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    1.06
    âķIJâķIJ
    1.05
    âĶĢâĶĢ
    1.02
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.99
    BALL
    0.82
    TER
    0.79
    Record
    0.78
    aneous
    0.78
    rics
    0.78
    --------
    0.77
    Act Density 0.013%

    No Known Activations