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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inclusion or exclusion in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -1.10
    stem
    -1.09
    thur
    -1.00
    aptic
    -1.00
    ¯¯¯¯¯¯¯¯
    -0.99
    mares
    -0.99
     raged
    -0.99
    sis
    -0.99
     temper
    -0.98
    HCR
    -0.98
    POSITIVE LOGITS
    ãģĨ
    1.13
    ãĤ½
    1.12
    ãĥ¯
    1.11
    ãĤ´
    1.08
     Include
    1.05
    ãĤ¯
    1.03
     prominently
    1.00
    ãĥĬ
    0.99
    rescent
    0.97
    clus
    0.96
    Act Density 1.039%

    No Known Activations