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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "captured" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yg
    -0.16
    ÅĽcie
    -0.15
    halt
    -0.15
    ozy
    -0.15
    iness
    -0.15
    636
    -0.15
    lijk
    -0.14
    ç¾½
    -0.14
    -muted
    -0.14
    595
    -0.14
    POSITIVE LOGITS
    uring
    0.31
    ivated
    0.30
    ured
    0.28
    ains
    0.27
    ivating
    0.27
    ivity
    0.25
    chas
    0.24
    URING
    0.23
    urable
    0.23
    ainless
    0.23
    Act Density 0.006%

    No Known Activations