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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of "base" or "based."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶĢâĶĢ
    -0.64
    ylon
    -0.62
     :(
    -0.57
    uv
    -0.55
    tes
    -0.55
    rawdownloadcloneembedreportprint
    -0.54
    ffield
    -0.53
    asar
    -0.53
     fulfilled
    -0.53
    ivering
    -0.53
    POSITIVE LOGITS
     blame
    0.98
     oneself
    0.91
     yourselves
    0.81
     ourselves
    0.80
     themselves
    0.78
    atively
    0.74
     emphasis
    0.71
     yourself
    0.71
    Pie
    0.70
     bets
    0.68
    Act Density 0.063%

    No Known Activations