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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a place, person, or event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" and its frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TRUE
    -0.67
     STA
    -0.65
     Scholarship
    -0.65
    ALSE
    -0.63
     SPR
    -0.63
    MSN
    -0.62
     NG
    -0.62
     ®
    -0.61
    !!!!!!!!
    -0.61
     YES
    -0.61
    POSITIVE LOGITS
     defiance
    0.91
     retaliation
    0.91
     remarks
    0.82
     spite
    0.82
     what
    0.82
     response
    0.80
     anticipation
    0.79
     advance
    0.76
     unprecedented
    0.76
     conjunction
    0.75
    Act Density 0.187%

    No Known Activations