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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ushman
    -0.15
    ayne
    -0.15
    rient
    -0.15
    isia
    -0.15
    ÙĪÙĨد
    -0.15
    ustum
    -0.14
    ffa
    -0.14
    visa
    -0.14
    egl
    -0.14
     vid
    -0.14
    POSITIVE LOGITS
     onResponse
    0.15
    dee
    0.14
    eos
    0.14
    -corner
    0.14
    kits
    0.13
    çĴ
    0.13
     hv
    0.13
    gary
    0.13
     Veranst
    0.13
    a
    0.13
    Act Density 0.061%

    No Known Activations