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

    Neuronpedia

    INDEX
    Explanations

    words that convey a sense of admiration or high quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goodman
    -0.16
    erin
    -0.14
    shiv
    -0.14
    mensaje
    -0.14
    ways
    -0.14
    алÑĥ
    -0.14
    å¾
    -0.14
    935
    -0.14
    esian
    -0.14
    WM
    -0.14
    POSITIVE LOGITS
    ingly
    0.22
    ively
    0.21
    ably
    0.19
    -looking
    0.17
    ابط
    0.17
    eus
    0.16
     Pods
    0.16
    oir
    0.15
    oes
    0.15
    orate
    0.15
    Act Density 0.027%

    No Known Activations