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

    Neuronpedia

    INDEX
    Explanations

    modal verbs related to possibility and necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    instein
    -0.16
    lyn
    -0.15
    iners
    -0.15
    rani
    -0.14
    _consts
    -0.14
    à¹Ģลย
    -0.14
    _DLL
    -0.14
    wend
    -0.14
    å§
    -0.14
    rand
    -0.14
    POSITIVE LOGITS
     they
    0.34
     we
    0.31
     it
    0.28
     они
    0.24
     вони
    0.23
     he
    0.22
    they
    0.21
     оно
    0.21
     you
    0.20
     she
    0.20
    Act Density 0.202%

    No Known Activations