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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "welcome" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    t
    -0.16
    yen
    -0.15
     cuff
    -0.15
     Gould
    -0.15
    eced
    -0.15
    eff
    -0.15
    ortion
    -0.15
    ythe
    -0.15
    lej
    -0.14
    quia
    -0.14
    POSITIVE LOGITS
    coming
    0.24
    comed
    0.21
    les
    0.19
    hausen
    0.19
    nesday
    0.18
    wyn
    0.18
    summer
    0.17
    .SizeMode
    0.17
    comes
    0.17
     Wel
    0.17
    Act Density 0.005%

    No Known Activations