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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Chopper"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cho" and related names, especially within contexts that imply a recurring theme or subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HAEL
    -0.91
    DEF
    -0.80
    PORT
    -0.78
    IRO
    -0.78
    HCR
    -0.76
    Phill
    -0.75
    DERR
    -0.73
    ALD
    -0.73
    ADE
    -0.72
     Interpret
    -0.71
    POSITIVE LOGITS
     cho
    1.04
    ppy
    0.89
    ptic
    0.88
    bably
    0.80
    ¸
    0.80
    pper
    0.80
    ffield
    0.77
    chy
    0.75
    ewater
    0.74
    bled
    0.74
    Act Density 0.016%

    No Known Activations