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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "caval" or "cave."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esome
    -0.15
    OutOfBounds
    -0.15
    actory
    -0.15
    deen
    -0.14
    DIRECT
    -0.14
    ÙģØ©
    -0.14
    ENTA
    -0.14
    mpar
    -0.14
    JOR
    -0.14
    ÙIJÙĥ
    -0.14
    POSITIVE LOGITS
     cav
    0.22
    alc
    0.20
    tat
    0.18
    ilha
    0.18
     Cav
    0.18
    shed
    0.17
    ACE
    0.17
    irt
    0.17
    lier
    0.17
    eman
    0.17
    Act Density 0.013%

    No Known Activations