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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of amplification or large-scale effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itage
    -0.16
    oog
    -0.16
    oj
    -0.15
     Francis
    -0.15
    g
    -0.15
    oi
    -0.15
    ãĥ¼ãĥĸãĥ«
    -0.14
    enek
    -0.14
    actices
    -0.14
    combe
    -0.14
    POSITIVE LOGITS
     magn
    0.30
     Magn
    0.28
    ificent
    0.27
    olia
    0.26
    Magn
    0.25
    esium
    0.24
    itudes
    0.24
    ussen
    0.24
    itude
    0.23
    ITUDE
    0.22
    Act Density 0.007%

    No Known Activations