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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opard
    -0.16
     might
    -0.16
    ETO
    -0.15
    alement
    -0.15
    rip
    -0.15
    nio
    -0.15
     maybe
    -0.15
    ighb
    -0.14
    umbn
    -0.14
    ibbon
    -0.14
    POSITIVE LOGITS
     freely
    0.20
    onna
    0.18
    nard
    0.16
    939
    0.14
     anytime
    0.14
     occasions
    0.14
    zzle
    0.14
    ily
    0.14
    okies
    0.14
    972
    0.14
    Act Density 0.073%

    No Known Activations