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

    Neuronpedia

    INDEX
    Explanations

    the phrase "in the" followed by specific topics or locations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the preposition "in" indicating locations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOG
    -0.81
    CLASSIFIED
    -0.76
    NOW
    -0.76
    CHA
    -0.74
    EH
    -0.70
    ãĤ£
    -0.70
    ENTS
    -0.69
    è»
    -0.69
    REF
    -0.65
    =]
    -0.64
    POSITIVE LOGITS
    clusions
    1.20
     lieu
    1.17
     favor
    1.16
     vitro
    1.13
     accordance
    1.12
     favour
    1.12
    animate
    1.10
    effic
    1.09
     disguise
    1.07
    efficiency
    1.05
    Act Density 0.366%

    No Known Activations