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

    Neuronpedia

    INDEX
    Explanations

    words related to electrical wiring or wire fraud

    oai_token-act-pair · gpt-3.5-turbo

    references to "wire" and associated terms related to wire fraud and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivia
    -0.82
    BIP
    -0.75
    ãħĭ
    -0.69
     Bailey
    -0.67
    olute
    -0.65
     Pend
    -0.64
    uum
    -0.63
     contestants
    -0.61
    idity
    -0.61
    inia
    -0.61
    POSITIVE LOGITS
    lessly
    1.41
    tap
    1.16
    fram
    1.13
    frame
    1.11
    frames
    1.07
    wire
    1.05
    haired
    0.99
     mesh
    0.96
    cut
    0.89
    quartered
    0.87
    Act Density 0.028%

    No Known Activations