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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and probabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    átka
    -0.15
     Rad
    -0.14
    afi
    -0.14
    XHR
    -0.14
    acy
    -0.14
    .bank
    -0.13
    üc
    -0.13
    uced
    -0.13
     Recon
    -0.13
    orama
    -0.13
    POSITIVE LOGITS
    ãĥ«ãĥī
    0.16
    rieve
    0.15
    uld
    0.14
    HIR
    0.14
    AIT
    0.14
    yre
    0.14
    utar
    0.14
    roz
    0.14
    avez
    0.14
    atore
    0.14
    Act Density 0.194%

    No Known Activations