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

    Neuronpedia

    INDEX
    Explanations

    phrases that express capabilities or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     positifs
    -0.70
     StatelessWidget
    -0.68
    rashed
    -0.67
    utnik
    -0.67
     Fros
    -0.66
    eningrad
    -0.65
    principalColumn
    -0.64
     Martens
    -0.63
     suspicions
    -0.63
     Kirs
    -0.62
    POSITIVE LOGITS
     abilities
    1.52
     ability
    1.52
     Ability
    1.43
    Ability
    1.32
     Abilities
    1.31
     capability
    1.22
    Abilities
    1.17
     capabilities
    1.13
     Able
    1.10
     able
    1.07
    Act Density 0.082%

    No Known Activations