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

    Neuronpedia

    INDEX
    Explanations

    references to safety and crash test evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    longleftrightarrow
    -0.17
     haut
    -0.16
    urai
    -0.15
    ccione
    -0.15
    æķ·
    -0.14
    umbo
    -0.14
    conc
    -0.14
     Hindered
    -0.14
    FRING
    -0.14
    agu
    -0.14
    POSITIVE LOGITS
     low
    0.20
     inexpensive
    0.20
    low
    0.20
     elemental
    0.18
     Low
    0.18
     elementary
    0.17
     budget
    0.17
     simple
    0.17
     cheap
    0.17
    ons
    0.17
    Act Density 0.171%

    No Known Activations