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

    Neuronpedia

    INDEX
    Explanations

    instances where an action or event leads to a specific outcome or consequence

    oai_token-act-pair · gpt-3.5-turbo

    phrasal structures indicating causation or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assets
    -0.80
    disabled
    -0.75
    rex
    -0.73
    limits
    -0.71
    posted
    -0.69
    employed
    -0.68
    phia
    -0.67
    oshenko
    -0.66
    Posted
    -0.65
    chanted
    -0.65
    POSITIVE LOGITS
     realization
    0.77
     turnaround
    0.73
     breakthrough
    0.73
     chase
    0.69
     wedge
    0.69
     elim
    0.68
    emonic
    0.67
     shootout
    0.67
    forth
    0.66
    ardless
    0.66
    Act Density 0.192%

    No Known Activations