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

    Neuronpedia

    INDEX
    Explanations

    references to reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SuppressLint
    -0.76
    TemporalType
    -0.59
    DrawerToggle
    -0.58
    ause
    -0.56
     astore
    -0.55
    السكان
    -0.53
    ge
    -0.50
     Tex
    -0.50
     carbon
    -0.47
     sub
    -0.47
    POSITIVE LOGITS
     reputation
    0.94
    Password
    0.91
     réputation
    0.89
     statue
    0.89
     Reputation
    0.89
     painting
    0.84
    statue
    0.82
     reputación
    0.81
     dipinto
    0.81
     Integrity
    0.81
    Act Density 0.053%

    No Known Activations