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

    Neuronpedia

    INDEX
    Explanations

    phrases that justify actions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lland
    -0.16
    zin
    -0.15
    Tube
    -0.15
     Tube
    -0.14
    ela
    -0.14
    Leod
    -0.14
    igure
    -0.14
    Gatt
    -0.14
    éĤ£ç§į
    -0.13
    esModule
    -0.13
    POSITIVE LOGITS
     mere
    0.18
    anga
    0.18
     doesn
    0.15
    mere
    0.15
    åı¸
    0.14
    kus
    0.14
    ABCDEFGHIJKLMNOP
    0.14
     Conj
    0.14
    chal
    0.14
     shouldn
    0.14
    Act Density 0.077%

    No Known Activations