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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing expectations or beliefs connected to actions and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uya
    -0.16
     Leban
    -0.16
    igel
    -0.15
    762
    -0.15
    childs
    -0.14
    abis
    -0.14
    erus
    -0.14
     деле
    -0.13
     stri
    -0.13
     Independence
    -0.13
    POSITIVE LOGITS
    udit
    0.15
    appa
    0.15
    obuf
    0.14
    awah
    0.14
    nee
    0.14
    entes
    0.14
    umen
    0.14
    elop
    0.14
     Certain
    0.14
    гоÑĤ
    0.14
    Act Density 0.088%

    No Known Activations