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

    Neuronpedia

    INDEX
    Explanations

    patterns and frequencies of character combinations in strings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.82
    OGND
    -0.76
     GenerationType
    -0.74
    __':
    -0.73
    '],'
    -0.71
    "]]
    -0.69
     للمعارف
    -0.69
    saraba
    -0.68
    SourceChecksum
    -0.68
    etheless
    -0.67
    POSITIVE LOGITS
    tttt
    0.53
    eee
    0.53
    ttt
    0.52
    oooooo
    0.48
    Uninitialized
    0.47
    ooooo
    0.45
    upun
    0.45
    jkl
    0.45
    oooo
    0.44
    z
    0.44
    Act Density 0.548%

    No Known Activations