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

    Neuronpedia

    INDEX
    Explanations

    words related to underground locations or activities

    oai_token-act-pair · gpt-3.5-turbo

    the term "ter" as part of various phrases or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELS
    -0.74
    ï¸
    -0.70
    ¬¼
    -0.67
     Pace
    -0.64
    olulu
    -0.61
    uncture
    -0.60
    ħĭ
    -0.60
     undermin
    -0.60
    STON
    -0.58
     circum
    -0.58
    POSITIVE LOGITS
    geist
    1.29
    ranean
    1.21
    rors
    1.07
    rible
    1.03
    tainment
    0.99
    rane
    0.99
    flies
    0.95
    brate
    0.91
    brates
    0.90
    ribly
    0.89
    Act Density 0.025%

    No Known Activations