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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "those" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¯
    -0.18
    ndon
    -0.15
    ÑĨип
    -0.15
    .scalablytyped
    -0.15
    ì§ĵ
    -0.14
    tober
    -0.14
     SOUR
    -0.14
    .LayoutStyle
    -0.14
    सर
    -0.14
    rew
    -0.14
    POSITIVE LOGITS
    curity
    0.18
    eza
    0.16
    Ļ¨
    0.15
    stva
    0.15
    caff
    0.14
     beiden
    0.14
    okin
    0.14
    ÙĪغ
    0.14
    caffold
    0.14
    ylko
    0.14
    Act Density 0.050%

    No Known Activations