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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical interactions or processes

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃs
    -0.72
    ONSORED
    -0.72
    Leaks
    -0.71
    edia
    -0.68
    éŃĶ
    -0.67
    lis
    -0.65
    LOG
    -0.64
    ente
    -0.64
    INS
    -0.64
    è»
    -0.63
    POSITIVE LOGITS
     assorted
    0.93
     redistributed
    0.81
     consequently
    0.77
     hence
    0.76
     therefore
    0.74
    romeda
    0.73
     distribute
    0.71
     kindred
    0.71
     thus
    0.70
     other
    0.70
    Act Density 0.522%

    No Known Activations