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

    Neuronpedia

    INDEX
    Explanations

    patterns of language that indicate evaluation, frequency, or emphasis related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĤ
    -0.14
    Ìĥ
    -0.14
    SHORT
    -0.14
    esian
    -0.14
    olley
    -0.14
    asurable
    -0.13
     Provid
    -0.13
     empt
    -0.13
    .beginPath
    -0.13
     VÅ¡ech
    -0.13
    POSITIVE LOGITS
     continued
    0.29
     concern
    0.28
     continue
    0.28
     continues
    0.25
    continue
    0.25
     concerns
    0.25
     unchanged
    0.25
    maint
    0.24
     interest
    0.24
    continued
    0.23
    Act Density 0.018%

    No Known Activations