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

    Neuronpedia

    INDEX
    Explanations

    the word "whatever" and its related variations, indicating a focus on expressions of indifference or many possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enis
    -0.15
    scape
    -0.14
    jamin
    -0.14
    Ñģка
    -0.14
    Ħĸ
    -0.14
    HITE
    -0.13
    uner
    -0.13
    ossier
    -0.13
    soon
    -0.13
    inel
    -0.13
    POSITIVE LOGITS
     else
    0.20
    .truth
    0.15
    dÃŃ
    0.15
    izr
    0.14
    eld
    0.14
    elder
    0.14
    ase
    0.14
    fee
    0.14
    ly
    0.14
     kinds
    0.14
    Act Density 0.015%

    No Known Activations