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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paren
    -0.71
     Seym
    -0.68
     horizont
    -0.66
     vulner
    -0.66
    accompan
    -0.63
    ilaterally
    -0.63
    tun
    -0.61
     diction
    -0.60
    anamo
    -0.58
     disadvant
    -0.58
    POSITIVE LOGITS
     celebrate
    0.85
    asted
    0.77
    ggles
    0.77
    ilet
    0.76
     provide
    0.75
    pload
    0.75
     avoid
    0.74
    asty
    0.73
     update
    0.73
     enlarge
    0.73
    Act Density 0.050%

    No Known Activations