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

    Neuronpedia

    INDEX
    Explanations

    verb phrases indicating someone holding a position or title

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" in various contexts, indicating roles or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usra
    -0.66
    Enlarge
    -0.65
    itiveness
    -0.64
    ron
    -0.63
    ru
    -0.63
    notice
    -0.63
    itious
    -0.63
    rax
    -0.63
    rogen
    -0.62
    FFFF
    -0.61
    POSITIVE LOGITS
    pired
    1.12
    pires
    1.10
    bestos
    0.96
    piring
    0.91
     well
    0.91
     opposed
    0.87
    phy
    0.84
     evidenced
    0.84
    criptions
    0.82
     follows
    0.82
    Act Density 0.205%

    No Known Activations