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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions and interactions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Week
    -0.80
    onymous
    -0.76
    MK
    -0.75
    ADVERTISEMENT
    -0.73
    actionDate
    -0.72
    successful
    -0.71
    Planet
    -0.71
    unique
    -0.71
    NULL
    -0.70
    usterity
    -0.70
    POSITIVE LOGITS
     then
    1.04
     thence
    0.95
     vo
    0.92
     thereby
    0.90
     THEN
    0.89
     consequently
    0.87
     thus
    0.85
     brim
    0.84
     secondly
    0.83
     throats
    0.81
    Act Density 0.303%

    No Known Activations