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

    Neuronpedia

    INDEX
    Explanations

    phrases related to treatment and perceptions of individuals in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.44
     readily
    -0.43
     noDo
    -0.43
     يتيمه
    -0.42
    GEBURTSDATUM
    -0.42
     successful
    -0.41
    さすがに
    -0.41
     reliable
    -0.39
    successful
    -0.39
     ausreich
    -0.38
    POSITIVE LOGITS
     differently
    1.24
     according
    0.71
     diffé
    0.71
     similarly
    0.66
     inconsist
    0.66
     Differ
    0.63
    differ
    0.62
     accordingly
    0.61
     incorrectly
    0.61
    according
    0.58
    Act Density 0.907%

    No Known Activations