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

    Neuronpedia

    INDEX
    Explanations

    assertive language and expressions of opinion or argumentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.60
    UnusedPrivate
    -0.50
     dlatego
    -0.49
    fsp
    -0.49
     inoltre
    -0.48
     esperança
    -0.47
    :
    -0.47
    。
    -0.46
     elegans
    -0.46
    veck
    -0.45
    POSITIVE LOGITS
     itſelf
    0.93
     technically
    0.77
     faſt
    0.76
     myſelf
    0.74
     ſmall
    0.74
     Reſ
    0.73
     fufficient
    0.72
     {},
    0.71
     fubject
    0.70
     poffible
    0.70
    Act Density 0.331%

    No Known Activations