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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter "b" and related variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    l
    -0.27
    oles
    -0.26
    ìĿ´
    -0.24
    ar
    -0.21
    lad
    -0.21
    oi
    -0.21
    oj
    -0.20
    rp
    -0.20
    oor
    -0.20
    oft
    -0.20
    POSITIVE LOGITS
    eyond
    0.21
    ey
    0.19
    bery
    0.19
    ek
    0.18
    eye
    0.18
    ale
    0.18
    egal
    0.18
    egg
    0.18
    ellow
    0.17
    ocop
    0.17
    Act Density 0.077%

    No Known Activations