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

    Neuronpedia

    INDEX
    Explanations

    negative emotional experiences or actions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to trauma and emotional pain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interchange
    -0.61
    VL
    -0.61
     indicating
    -0.58
    uploads
    -0.57
     successors
    -0.57
    ifer
    -0.57
     indications
    -0.56
    suggest
    -0.56
     interestingly
    -0.56
     alleging
    -0.56
    POSITIVE LOGITS
     oneself
    1.04
     Yourself
    0.81
     yourself
    0.72
    arenthood
    0.69
    thood
    0.68
     shitty
    0.66
     sweaty
    0.64
     ______
    0.63
     solitude
    0.61
     drunk
    0.61
    Act Density 0.898%

    No Known Activations