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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an abrupt or unexpected change in events or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dayName
    -0.69
    blance
    -0.68
    gee
    -0.66
    irs
    -0.63
    nes
    -0.63
    ombat
    -0.62
    assembly
    -0.62
    OGR
    -0.61
    ertodd
    -0.57
     rematch
    -0.56
    POSITIVE LOGITS
     sudden
    1.00
     us
    0.83
    llor
    0.72
     these
    0.68
    ahu
    0.68
     humanity
    0.66
     Sparkle
    0.61
    these
    0.60
    course
    0.60
    udes
    0.60
    Act Density 0.054%

    No Known Activations