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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "giant."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.74
     rendus
    -0.68
     Alamofire
    -0.68
     onAnimation
    -0.62
     Malk
    -0.59
     intime
    -0.59
     Ueb
    -0.59
     Wanderers
    -0.59
     snowboard
    -0.58
     WRX
    -0.58
    POSITIVE LOGITS
    Prosecutors
    0.72
     prosecutors
    0.71
     Prosec
    0.69
    Prosec
    0.68
     Prosecution
    0.65
    giant
    0.63
     prosecute
    0.63
    Pros
    0.62
    тельстве
    0.62
     Pros
    0.62
    Act Density 0.027%

    No Known Activations