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

    Neuronpedia

    INDEX
    Explanations

    observations related to emotional or physical states and situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "having" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     References
    -0.63
     reserv
    -0.63
     Unlock
    -0.60
     Offline
    -0.60
    being
    -0.59
     anticipating
    -0.58
     premise
    -0.58
     Survivors
    -0.57
     presenting
    -0.57
     Teaching
    -0.56
    POSITIVE LOGITS
     trouble
    1.02
     fun
    0.89
     conversations
    0.85
     nightmares
    0.84
    rodu
    0.81
     discussions
    0.81
     intercourse
    0.81
     difficulties
    0.76
     affairs
    0.76
     dealings
    0.75
    Act Density 0.100%

    No Known Activations