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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     convol
    -0.76
    llor
    -0.73
     destro
    -0.72
     thous
    -0.66
     fortun
    -0.65
     vulner
    -0.63
    alore
    -0.62
    wagon
    -0.62
     blat
    -0.60
    edIn
    -0.60
    POSITIVE LOGITS
     lieu
    1.08
    clusions
    0.99
     accordance
    0.99
    clus
    0.93
     conjunction
    0.91
    patient
    0.86
     favor
    0.83
     vitro
    0.83
     addition
    0.83
    ordinate
    0.82
    Act Density 0.242%

    No Known Activations