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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a person's success or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CTO
    -0.60
    posables
    -0.57
    PasswordEncoder
    -0.57
     Lanz
    -0.56
    Bé
    -0.54
    jsonwebtoken
    -0.53
    sopa
    -0.53
     href
    -0.52
     CanadaChoose
    -0.52
     Mahat
    -0.51
    POSITIVE LOGITS
     thrived
    1.08
     prosper
    1.05
     thrive
    1.04
     thrives
    0.99
     réuss
    0.90
    دانشنامهٔ
    0.83
     flourish
    0.83
     flourished
    0.82
    ConstraintMaker
    0.78
     thriving
    0.77
    Act Density 0.163%

    No Known Activations