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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to speculative or reported events

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate speculation or uncertainty regarding projects and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utics
    -0.81
    vet
    -0.78
    tics
    -0.76
    arden
    -0.74
    cloth
    -0.74
    adier
    -0.72
    kk
    -0.72
    etics
    -0.72
    galitarian
    -0.71
    ande
    -0.71
    POSITIVE LOGITS
     amount
    0.80
     atmospheric
    0.80
     annual
    0.78
     fourth
    0.77
     number
    0.76
     outcome
    0.76
     civilian
    0.75
     arrival
    0.75
     occurrence
    0.73
     unauthorized
    0.72
    Act Density 0.108%

    No Known Activations