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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms that imply subtlety or delicacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amarin
    -0.19
    slick
    -0.16
    occo
    -0.16
    оÑĢе
    -0.15
    PLIT
    -0.15
    nit
    -0.15
    agli
    -0.15
    agine
    -0.14
    ertz
    -0.14
    etat
    -0.14
    POSITIVE LOGITS
    tics
    0.16
     ucfirst
    0.15
    ernet
    0.15
    à¹Ĩ
    0.15
     Atom
    0.15
    RL
    0.14
     gentle
    0.14
     ucwords
    0.14
    ise
    0.14
    133
    0.14
    Act Density 0.064%

    No Known Activations