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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specificity and selection criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    benchmark
    -0.15
     COPYING
    -0.14
     Tib
    -0.14
    ADDE
    -0.13
    REAK
    -0.13
    PCP
    -0.13
    жÑĥ
    -0.13
     gsi
    -0.13
    #ab
    -0.13
    eger
    -0.13
    POSITIVE LOGITS
     specific
    0.20
    -specific
    0.19
    specific
    0.17
    Specific
    0.16
    oric
    0.15
    uan
    0.15
     potions
    0.15
    _specific
    0.14
     especÃŃf
    0.14
     particular
    0.14
    Act Density 0.220%

    No Known Activations