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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adele
    -0.19
    ties
    -0.17
    mite
    -0.16
    erosis
    -0.15
    fal
    -0.15
    ece
    -0.15
    mh
    -0.14
    ively
    -0.14
    alia
    -0.14
    LOAT
    -0.14
    POSITIVE LOGITS
    geries
    0.29
     sake
    0.29
    bidden
    0.27
    -profit
    0.25
     purposes
    0.24
     instance
    0.24
    aging
    0.24
    ays
    0.24
    age
    0.23
    asm
    0.20
    Act Density 0.732%

    No Known Activations