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

    Neuronpedia

    INDEX
    Explanations

    words related to complexity and emotional intensity

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe complex or challenging situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    weeney
    -0.71
    adelphia
    -0.70
    xia
    -0.69
    otin
    -0.67
    iens
    -0.66
    gone
    -0.66
    arser
    -0.65
    paio
    -0.64
    rera
    -0.64
    geons
    -0.64
    POSITIVE LOGITS
     alike
    1.59
     respectively
    0.94
    entimes
    0.72
     Dragonbound
    0.72
     truths
    0.69
     combinations
    0.62
     importantly
    0.62
     attRot
    0.61
    -|
    0.60
     excuses
    0.60
    Act Density 0.492%

    No Known Activations