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

    Neuronpedia

    INDEX
    Explanations

    words indicating significance or importance related to specific subjects or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .getSelection
    -0.16
    itori
    -0.15
    leton
    -0.15
    imals
    -0.15
    baar
    -0.15
    zp
    -0.14
    lbrakk
    -0.14
     miêu
    -0.14
     Parkway
    -0.14
    ikt
    -0.14
    POSITIVE LOGITS
     treat
    0.19
     treating
    0.19
     treatments
    0.18
     Treatment
    0.18
     treatment
    0.18
     mir
    0.17
     mirror
    0.16
     Freed
    0.16
     Treat
    0.16
     mirrors
    0.16
    Act Density 0.020%

    No Known Activations