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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional and physical impacts of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roz
    -0.15
    érer
    -0.14
    impan
    -0.14
    iesz
    -0.14
    .Deserialize
    -0.13
    coma
    -0.13
    .constraints
    -0.13
    isis
    -0.13
     encounter
    -0.13
    iative
    -0.13
    POSITIVE LOGITS
     being
    0.22
    being
    0.18
    erc
    0.17
     sendo
    0.16
     innov
    0.15
     coming
    0.15
     becoming
    0.15
     Being
    0.14
    iks
    0.14
    coming
    0.14
    Act Density 0.274%

    No Known Activations