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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating addition, particularly in a negative context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating additions or contributions to a situation or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHAT
    -0.77
    glers
    -0.63
    iker
    -0.61
     Reporter
    -0.60
    cko
    -0.59
    rowth
    -0.59
     Dane
    -0.59
    soever
    -0.58
    Released
    -0.58
    leground
    -0.58
    POSITIVE LOGITS
     compensate
    0.73
    otos
    0.68
    ventory
    0.67
     enhance
    0.67
     counteract
    0.65
     scenery
    0.65
     strengthen
    0.64
     bolster
    0.63
     prominence
    0.63
     shore
    0.63
    Act Density 0.063%

    No Known Activations