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

    Neuronpedia

    INDEX
    Explanations

    the word "these" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dge
    -0.16
    ibold
    -0.15
    ebra
    -0.15
    ãĥ
    -0.15
    endon
    -0.15
    FFFFFF
    -0.14
    ady
    -0.14
    cko
    -0.14
    .springboot
    -0.14
    rens
    -0.14
    POSITIVE LOGITS
    ario
    0.16
    aris
    0.16
    ilos
    0.15
     Trio
    0.15
     Honey
    0.14
     acum
    0.14
     Hastings
    0.14
    idir
    0.14
     Hedge
    0.14
    inin
    0.14
    Act Density 0.094%

    No Known Activations