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

    Neuronpedia

    INDEX
    Explanations

    terms related to negotiation and agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ières
    -0.16
    ãĥ¤
    -0.15
    TCP
    -0.15
    isbury
    -0.14
     Gott
    -0.14
     Fancy
    -0.14
    edeki
    -0.14
     shedding
    -0.14
    alker
    -0.14
    acter
    -0.13
    POSITIVE LOGITS
    hetto
    0.16
    olson
    0.15
    atively
    0.15
    abler
    0.15
    vous
    0.15
    ños
    0.14
    ably
    0.14
    wan
    0.14
     fred
    0.14
    ÑĢин
    0.14
    Act Density 0.015%

    No Known Activations