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

    Neuronpedia

    INDEX
    Explanations

    phrases related to saving resources or money

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mith
    -0.17
    ophobia
    -0.16
    059
    -0.16
    uale
    -0.16
    è»
    -0.16
    soever
    -0.15
    seealso
    -0.15
    wner
    -0.15
    idon
    -0.14
    ally
    -0.14
    POSITIVE LOGITS
    /rest
    0.17
    aret
    0.15
    icular
    0.15
    /loose
    0.15
    aller
    0.15
    kus
    0.14
    inds
    0.14
    indow
    0.14
    illon
    0.14
    ellar
    0.14
    Act Density 0.039%

    No Known Activations