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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing quantity or degree, particularly the use of "so" with varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rica
    -0.15
     bestselling
    -0.15
    prit
    -0.15
    orig
    -0.14
    rof
    -0.14
    pard
    -0.14
    ousand
    -0.14
    -prepend
    -0.13
    odesk
    -0.13
    rico
    -0.13
    POSITIVE LOGITS
    oth
    0.18
    ars
    0.18
    jom
    0.17
    isson
    0.17
    -called
    0.16
    ething
    0.16
    ARS
    0.15
    ovit
    0.15
     far
    0.15
    strain
    0.15
    Act Density 0.068%

    No Known Activations