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
    álo
    -0.17
    idis
    -0.16
    ær
    -0.16
    ussen
    -0.16
    adel
    -0.15
    ako
    -0.14
    uniacid
    -0.14
    umble
    -0.14
    instr
    -0.14
    ovice
    -0.14
    POSITIVE LOGITS
    nt
    0.20
    iams
    0.16
    URRENT
    0.16
    've
    0.16
    ’ve
    0.15
    -be
    0.14
    /is
    0.14
     le
    0.14
    ering
    0.13
    standing
    0.13
    Act Density 0.218%

    No Known Activations