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

    Neuronpedia

    INDEX
    Explanations

    phrases related to monetary amounts or financial terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic measurements or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.80
    RAW
    -0.75
    ebook
    -0.72
    berry
    -0.70
    Chicken
    -0.70
    RAFT
    -0.69
    velt
    -0.69
    GR
    -0.69
    Roll
    -0.68
    draw
    -0.68
    POSITIVE LOGITS
     nominal
    1.08
    etheless
    1.02
     occas
    0.93
    ized
    0.90
    ominated
    0.89
    istic
    0.86
    istically
    0.83
    ised
    0.83
    ascus
    0.82
    umin
    0.80
    Act Density 0.012%

    No Known Activations