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

    Neuronpedia

    INDEX
    Explanations

    terms related to duplication and replication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rd
    -0.21
    ened
    -0.17
    alet
    -0.16
    way
    -0.15
    izu
    -0.15
    sg
    -0.15
    ley
    -0.15
     Král
    -0.15
    dpi
    -0.15
    monds
    -0.14
    POSITIVE LOGITS
    .deepcopy
    0.27
    /cop
    0.24
     exact
    0.24
    cat
    0.21
    exact
    0.20
    Exact
    0.19
     Exact
    0.17
    åĵģ
    0.16
    -cat
    0.16
    icking
    0.16
    Act Density 0.047%

    No Known Activations