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

    Neuronpedia

    INDEX
    Explanations

    scenes or descriptions that involve actions taking place in front of a specific location

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a physical position or location, specifically focusing on the concept of being "in front of" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zn
    -0.64
    Leaks
    -0.63
    ©¶æ
    -0.63
    sei
    -0.61
    cci
    -0.61
    chini
    -0.60
    ixtape
    -0.59
    IRO
    -0.59
    ajor
    -0.59
    ccording
    -0.58
    POSITIVE LOGITS
     of
    0.97
     thereof
    0.89
    aday
    0.81
    of
    0.80
    OF
    0.77
     row
    0.74
    screen
    0.72
    matter
    0.71
     rows
    0.69
    court
    0.68
    Act Density 0.013%

    No Known Activations