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

    Neuronpedia

    INDEX
    Explanations

    descriptions of injuries and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Agencies
    -0.15
    itu
    -0.14
     oxygen
    -0.14
     dust
    -0.14
     Grow
    -0.14
    unan
    -0.14
     Fires
    -0.14
    aln
    -0.13
     agencies
    -0.13
    ilian
    -0.13
    POSITIVE LOGITS
     spill
    0.28
     dri
    0.26
     mess
    0.26
     spills
    0.24
     pooling
    0.24
     pudd
    0.23
     pooled
    0.22
     overflow
    0.22
     spilled
    0.22
    mess
    0.22
    Act Density 0.109%

    No Known Activations