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

    Neuronpedia

    INDEX
    Explanations

    phrases related to change or progression over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causal relationships or changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pton
    -0.65
    LP
    -0.62
    phies
    -0.61
    advant
    -0.61
    trap
    -0.61
    anners
    -0.60
    nv
    -0.59
     remotely
    -0.59
    BACK
    -0.58
    nsics
    -0.58
    POSITIVE LOGITS
     Yen
    0.69
    Reloaded
    0.68
     inflation
    0.67
    flation
    0.62
    etheless
    0.61
     semantic
    0.60
     Niet
    0.60
     TOD
    0.59
    luster
    0.59
    ioxide
    0.58
    Act Density 0.404%

    No Known Activations