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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing information or details about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andi
    -0.16
    Äįka
    -0.15
    icorn
    -0.15
    ulo
    -0.15
    608
    -0.15
    IOR
    -0.14
    ITT
    -0.14
    Fluid
    -0.14
    aviors
    -0.14
    ulers
    -0.14
    POSITIVE LOGITS
     sake
    0.30
     purposes
    0.27
     reasons
    0.17
    ascus
    0.17
    ø
    0.16
     pe
    0.15
    yt
    0.14
    cheon
    0.14
    stub
    0.14
    zar
    0.14
    Act Density 0.618%

    No Known Activations