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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with quantities and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emma
    -0.15
    elay
    -0.14
    ivol
    -0.14
    ìĸ¸
    -0.14
    ë¹ĦìķĦ
    -0.13
    ascus
    -0.13
    ÏĢοί
    -0.13
    ì°¬
    -0.13
    iens
    -0.13
    ampton
    -0.13
    POSITIVE LOGITS
     common
    0.71
    common
    0.60
     commonplace
    0.53
     commonly
    0.52
    -common
    0.51
     Common
    0.49
     COMMON
    0.48
    Common
    0.47
    .common
    0.46
    常
    0.45
    Act Density 0.259%

    No Known Activations