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

    Neuronpedia

    INDEX
    Explanations

    phrases related to objectives or intended outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynchronize
    -0.15
    adio
    -0.15
    ÑĢек
    -0.15
    culo
    -0.15
    469
    -0.14
    oto
    -0.13
    اÙģÙĬØ©
    -0.13
    uh
    -0.13
    inate
    -0.13
    cid
    -0.13
    POSITIVE LOGITS
     toward
    0.30
     towards
    0.27
    Towards
    0.20
     Towards
    0.20
    owards
    0.19
    åIJij
    0.18
     hacia
    0.18
    ness
    0.17
     Tow
    0.17
    æĶ
    0.17
    Act Density 0.031%

    No Known Activations