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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal achievement and positive influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.83
    ictionary
    -0.78
    ancial
    -0.77
    ivist
    -0.77
    autical
    -0.75
    iction
    -0.71
    utterstock
    -0.71
     inconvenient
    -0.71
    archy
    -0.70
    OPA
    -0.69
    POSITIVE LOGITS
     teammates
    0.98
     Coach
    0.97
     him
    0.95
     teammate
    0.93
     rookies
    0.89
     Ronnie
    0.83
     Robbie
    0.81
     Reggie
    0.81
     coaching
    0.80
     Derrick
    0.80
    Act Density 0.185%

    No Known Activations