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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing the concept of impossibility or difficulty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENTA
    -0.16
    UPPORTED
    -0.16
    upported
    -0.16
    PN
    -0.15
    ebek
    -0.15
    fü
    -0.14
    enz
    -0.14
    umd
    -0.14
    isse
    -0.14
    -Mart
    -0.14
    POSITIVE LOGITS
     anyone
    0.16
    kova
    0.15
     any
    0.14
     impossible
    0.14
    602
    0.14
    singular
    0.14
    obus
    0.14
    icie
    0.14
     anybody
    0.14
    Impossible
    0.13
    Act Density 0.028%

    No Known Activations