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

    Neuronpedia

    INDEX
    Explanations

    terms related to life and life-saving concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gger
    -0.17
    dorf
    -0.15
    mpi
    -0.15
    pii
    -0.15
    furt
    -0.15
    ovit
    -0.15
    .openg
    -0.14
    antanamo
    -0.14
    zew
    -0.14
    gio
    -0.14
    POSITIVE LOGITS
    boat
    0.29
    boats
    0.28
    bu
    0.27
    -saving
    0.27
    hack
    0.26
     sciences
    0.26
    blood
    0.25
     saving
    0.25
     threatening
    0.25
    changing
    0.25
    Act Density 0.027%

    No Known Activations