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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "predictable" or related concepts indicating expected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eral
    -0.16
    olute
    -0.15
    hi
    -0.15
     Kiss
    -0.14
    well
    -0.14
    aternity
    -0.14
    ØŃÙĩ
    -0.14
    IDES
    -0.14
    ink
    -0.13
    elen
    -0.13
    POSITIVE LOGITS
    ÑĮко
    0.17
    vos
    0.15
     doz
    0.15
    amar
    0.15
    segue
    0.14
     posix
    0.14
    ypad
    0.13
    egov
    0.13
    iggins
    0.13
    artz
    0.13
    Act Density 0.001%

    No Known Activations