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

    Neuronpedia

    INDEX
    Explanations

    future intentions and commitments expressed with modal verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ist
    -0.06
    95
    -0.06
    ameleon
    -0.06
     Rendering
    -0.06
     witness
    -0.05
     suitable
    -0.05
    .listen
    -0.05
     Suitable
    -0.05
     rendering
    -0.05
    eller
    -0.05
    POSITIVE LOGITS
    rava
    0.09
    ãĥķãĤ
    0.08
    ãĤ«ãĥĨ
    0.08
    ãĥĭãĥĥãĤ¯
    0.08
    ırak
    0.08
     derece
    0.07
    madan
    0.07
    Magnitude
    0.07
    onia
    0.07
    akis
    0.07
    Act Density 0.013%

    No Known Activations