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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social events and actions

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and their occurrences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uber
    -0.82
    enary
    -0.79
    iple
    -0.77
    ibo
    -0.76
    UF
    -0.76
    isi
    -0.71
    yon
    -0.69
    rius
    -0.67
    raved
    -0.66
    ¬¼
    -0.66
    POSITIVE LOGITS
     whereas
    1.19
     although
    1.18
     albeit
    1.15
     though
    1.13
     but
    1.05
     which
    1.02
     however
    1.00
     namely
    0.96
     favoring
    0.95
     meanwhile
    0.94
    Act Density 0.724%

    No Known Activations