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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by locations or contexts

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" used in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     convol
    -0.64
    CLASSIFIED
    -0.57
     incumb
    -0.56
     ingred
    -0.56
     surpr
    -0.55
    username
    -0.54
    llor
    -0.54
    killed
    -0.54
     endors
    -0.53
     fortun
    -0.53
    POSITIVE LOGITS
     lieu
    1.11
     accordance
    1.06
     conjunction
    1.01
    ordinate
    0.99
     regards
    0.96
     vitro
    0.94
    clusions
    0.94
    clus
    0.93
     order
    0.90
    patient
    0.90
    Act Density 0.518%

    No Known Activations