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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating potential or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asaki
    -0.15
    BorderStyle
    -0.15
    anki
    -0.15
    iele
    -0.15
    sted
    -0.14
    keeping
    -0.14
    Ñĺ
    -0.14
    aml
    -0.14
    .scalablytyped
    -0.14
    cke
    -0.13
    POSITIVE LOGITS
    nt
    0.37
    ’ve
    0.32
    've
    0.32
     be
    0.30
     potentially
    0.26
     possibly
    0.26
     conce
    0.25
    NT
    0.23
    /w
    0.23
     well
    0.21
    Act Density 0.084%

    No Known Activations