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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey physical actions or significant emotional impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enos
    -0.15
     invasive
    -0.15
    èŀº
    -0.14
     incon
    -0.14
    arness
    -0.14
    eniable
    -0.14
    AGMA
    -0.14
    erea
    -0.14
    inea
    -0.14
    lemn
    -0.14
    POSITIVE LOGITS
     ncols
    0.16
    kos
    0.16
    oogle
    0.15
    icro
    0.15
    945
    0.15
    271
    0.14
     RCS
    0.14
     Noel
    0.14
    acf
    0.14
    anvas
    0.14
    Act Density 0.002%

    No Known Activations