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

    Neuronpedia

    INDEX
    Explanations

    references to "free" or non-restrictive concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jing
    -0.18
    ãĥ³ãĤ°
    -0.16
    /me
    -0.16
    lej
    -0.16
    soever
    -0.16
    cle
    -0.16
    c
    -0.15
    arith
    -0.15
    unts
    -0.15
    stanbul
    -0.15
    POSITIVE LOGITS
    bie
    0.22
    bies
    0.21
    /free
    0.21
    -ÑĤаки
    0.18
    bsd
    0.18
    -floating
    0.17
    zeitig
    0.16
    holm
    0.16
    /open
    0.16
    esktop
    0.16
    Act Density 0.055%

    No Known Activations