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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal agreements and processes

    oai_token-act-pair · gpt-3.5-turbo

    indications of feelings of uncertainty or hesitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.64
    Engineers
    -0.63
    weed
    -0.57
    photos
    -0.52
    advertising
    -0.51
     âĢº
    -0.50
     bleach
    -0.50
     Nile
    -0.50
    -0.49
    ---
    -0.49
    POSITIVE LOGITS
    hower
    0.77
     rul
    0.71
    ebted
    0.69
    ividual
    0.68
     condem
    0.62
    heric
    0.59
    opted
    0.58
    uilt
    0.57
    hovah
    0.57
    eport
    0.54
    Act Density 3.738%

    No Known Activations