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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events and actions happening chronologically

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the sequence of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .–
    -0.66
    ="/
    -0.66
     actionGroup
    -0.65
    ards
    -0.64
    osphere
    -0.63
    abal
    -0.62
    NAS
    -0.61
    ocracy
    -0.61
    ether
    -0.61
    ":"/
    -0.60
    POSITIVE LOGITS
    sequently
    1.00
    later
    0.84
    ward
    0.81
    sequent
    0.79
    Later
    0.79
     subsequent
    0.78
    ometime
    0.75
     thereafter
    0.75
    anwhile
    0.73
     later
    0.72
    Act Density 0.324%

    No Known Activations