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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allet
    -0.16
     Synthetic
    -0.15
    idel
    -0.14
    vit
    -0.14
    von
    -0.14
    Ł³
    -0.14
    inx
    -0.14
    ocator
    -0.14
    íĴį
    -0.13
    виÑĤ
    -0.13
    POSITIVE LOGITS
    ANCH
    0.16
     live
    0.15
     certain
    0.15
    .Atomic
    0.14
     Mills
    0.14
    ije
    0.14
    wl
    0.14
    ίγ
    0.14
    #.
    0.14
     Rolling
    0.14
    Act Density 0.553%

    No Known Activations