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

    Neuronpedia

    INDEX
    Explanations

    discussions about belief systems and their contrasts with materialistic or pragmatic concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suddenly
    -0.15
     bare
    -0.14
    506
    -0.13
    enary
    -0.13
     bara
    -0.13
     nob
    -0.13
    ATAL
    -0.13
    ÙħÙĬÙħ
    -0.13
    querque
    -0.13
     Jag
    -0.13
    POSITIVE LOGITS
    ings
    0.20
    ÂŃing
    0.19
    itr
    0.17
    ÑĢиÑģ
    0.17
    ability
    0.16
    ingt
    0.16
    /delete
    0.16
    ertype
    0.16
    able
    0.16
    ptions
    0.15
    Act Density 0.793%

    No Known Activations