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

    Neuronpedia

    INDEX
    Explanations

    expressions of capability and ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mors
    -0.86
    upsi
    -0.67
     massa
    -0.67
     Rees
    -0.67
     mors
    -0.65
     dwarfs
    -0.64
     seznam
    -0.64
    Krok
    -0.64
     empre
    -0.64
    DoubleQuotes
    -0.64
    POSITIVE LOGITS
     able
    1.82
     Able
    1.61
    Able
    1.50
     Ability
    1.39
     ability
    1.32
    Ability
    1.29
     abilities
    1.16
     Abilities
    1.04
    Abilities
    0.95
     unable
    0.95
    Act Density 0.064%

    No Known Activations