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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating growth, change, or escalation

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating growth, increase, or starting actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    peria
    -0.71
    bal
    -0.70
    croft
    -0.65
    aca
    -0.63
    claimer
    -0.61
    aun
    -0.60
     laun
    -0.60
    \-
    -0.59
    sac
    -0.59
    pell
    -0.58
    POSITIVE LOGITS
     steadily
    0.89
     increasingly
    0.86
     inex
    0.85
     pains
    0.83
    lass
    0.78
     lately
    0.71
     dangerously
    0.70
    edge
    0.69
     rapidly
    0.67
    Edge
    0.66
    Act Density 0.251%

    No Known Activations