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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making a decision

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "and" in various contexts within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DX
    -0.84
    Origin
    -0.70
    lav
    -0.70
    gest
    -0.69
    Shut
    -0.68
    uel
    -0.68
    CLAIM
    -0.67
    dayName
    -0.67
    UTC
    -0.66
    BL
    -0.66
    POSITIVE LOGITS
     thereby
    1.32
     consequently
    1.27
     thus
    1.27
     hence
    1.20
     therefore
    1.18
     secondly
    1.10
     hopefully
    1.03
     furthermore
    1.01
     thence
    0.99
     eventually
    0.99
    Act Density 0.434%

    No Known Activations