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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lessly
    -0.16
    vided
    -0.15
    opak
    -0.15
    gether
    -0.14
    ún
    -0.14
    mdp
    -0.14
    izzard
    -0.14
    ìĭľìĺ¤
    -0.14
    wicklung
    -0.13
    .appendTo
    -0.13
    POSITIVE LOGITS
     going
    0.25
     ramps
    0.24
     ramp
    0.23
    coming
    0.23
    etime
    0.22
    Going
    0.22
     again
    0.22
    inous
    0.21
    er
    0.21
    eness
    0.21
    Act Density 0.038%

    No Known Activations