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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possibilities or predictions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rones
    -0.78
    ĸļ
    -0.69
    enary
    -0.67
    ulously
    -0.67
    strous
    -0.66
    ãĥ¼ãĥ«
    -0.66
    anwhile
    -0.66
    shall
    -0.65
    enaries
    -0.64
     allege
    -0.61
    POSITIVE LOGITS
     able
    1.16
     tempted
    1.10
     considered
    1.01
     construed
    1.00
     forgiven
    1.00
     swayed
    0.96
     regarded
    0.93
     viewed
    0.93
     mistaken
    0.89
    acons
    0.86
    Act Density 0.131%

    No Known Activations