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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference and superlatives related to experiences, opportunities, or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inen
    -0.16
    inem
    -0.14
    olars
    -0.14
    ãģŃ
    -0.14
     ourselves
    -0.14
     bem
    -0.14
    zza
    -0.14
    913
    -0.13
     modal
    -0.13
    òa
    -0.13
    POSITIVE LOGITS
     thing
    0.36
     Thing
    0.25
    thing
    0.25
    Thing
    0.23
     coisa
    0.21
     things
    0.20
     EVER
    0.20
     ever
    0.18
     anyone
    0.18
     cosa
    0.18
    Act Density 0.087%

    No Known Activations