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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "think" and its variations, indicating a focus on thoughts and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anik
    -0.16
    ez
    -0.16
    zman
    -0.15
    igham
    -0.15
    entiful
    -0.15
    enties
    -0.15
    /by
    -0.15
    asar
    -0.14
    .met
    -0.14
    culate
    -0.14
    POSITIVE LOGITS
    oad
    0.15
    AO
    0.14
    maj
    0.14
    lessly
    0.14
    fulness
    0.14
     about
    0.14
    象
    0.14
    enny
    0.14
     Bib
    0.13
     alike
    0.13
    Act Density 0.078%

    No Known Activations