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

    Neuronpedia

    INDEX
    Explanations

    actions and expressions indicating agreement or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loroethene
    -0.53
    цездатний
    -0.52
    Lep
    -0.48
    ruik
    -0.44
    cuit
    -0.43
     Lep
    -0.43
    bans
    -0.42
    arj
    -0.41
    bino
    -0.41
    lü
    -0.41
    POSITIVE LOGITS
     head
    1.67
     heads
    1.55
     Head
    1.53
    Head
    1.47
    head
    1.42
     HEAD
    1.39
     Heads
    1.34
    Heads
    1.27
    heads
    1.23
    HEAD
    1.20
    Act Density 0.111%

    No Known Activations