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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating gradual loss or reduction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating gradual reduction or decrease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.66
    enegger
    -0.64
    leans
    -0.63
    immer
    -0.63
    geries
    -0.60
    sit
    -0.60
    TPPStreamerBot
    -0.59
    arters
    -0.59
     Titus
    -0.59
    ammers
    -0.58
    POSITIVE LOGITS
     feathers
    0.76
     havoc
    0.76
     roots
    0.75
    wards
    0.74
     shred
    0.72
     excess
    0.71
     scraps
    0.71
     limbs
    0.69
     chunks
    0.68
     bushes
    0.68
    Act Density 0.091%

    No Known Activations