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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the timing of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating events or actions that are occurring or reporting on developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dden
    -0.83
    guided
    -0.83
    ee
    -0.77
    urse
    -0.76
    oller
    -0.75
    rendered
    -0.75
    ignty
    -0.74
    raid
    -0.74
    olor
    -0.74
    oru
    -0.73
    POSITIVE LOGITS
     undone
    0.96
     alive
    0.76
     amid
    0.73
     forward
    0.72
    backs
    0.71
     Forth
    0.70
     ashore
    0.69
     amidst
    0.69
     back
    0.68
     testament
    0.68
    Act Density 0.050%

    No Known Activations