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

    Neuronpedia

    INDEX
    Explanations

    references to trees or related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iras
    -0.19
    aries
    -0.17
    GGLE
    -0.17
    ordes
    -0.17
    undan
    -0.16
    ηÏĤ
    -0.16
    marine
    -0.15
    lies
    -0.14
    ARRIER
    -0.14
    ivate
    -0.14
    POSITIVE LOGITS
     trunk
    0.25
    house
    0.23
     branches
    0.22
    cko
    0.21
     branch
    0.21
     bark
    0.20
    branch
    0.20
     limbs
    0.19
    /tree
    0.19
     sap
    0.19
    Act Density 0.025%

    No Known Activations