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

    Neuronpedia

    INDEX
    Explanations

    words related to creation, implementation, or production processes

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.74
    Neg
    -0.67
    luaj
    -0.65
    å£
    -0.65
    zn
    -0.64
    iever
    -0.63
    ivari
    -0.63
     disarm
    -0.61
    herty
    -0.60
    netflix
    -0.59
    POSITIVE LOGITS
    redients
    1.19
    tons
    0.94
    HAM
    0.83
    athering
    0.72
     Procedure
    0.72
    ales
    0.69
    ulate
    0.68
    GGGGGGGG
    0.68
    hots
    0.64
    rat
    0.64
    Act Density 0.071%

    No Known Activations