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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating upcoming trends or significant developments

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating trends or new developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _.
    -0.77
    Downloadha
    -0.74
    ignt
    -0.68
    events
    -0.68
    cies
    -0.66
    each
    -0.65
    acts
    -0.65
     conventions
    -0.65
    rimination
    -0.64
    idents
    -0.63
    POSITIVE LOGITS
     casualty
    1.00
     logical
    0.82
     gateway
    0.78
     evolution
    0.72
     frontier
    0.72
     trendy
    0.70
     inspiration
    0.68
     gasp
    0.68
     conduit
    0.68
     backbone
    0.68
    Act Density 0.153%

    No Known Activations