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

    Neuronpedia

    INDEX
    Explanations

    information or updates that someone might have missed or needs to know

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to addressing the reader and prompting them to consider specific information or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kong
    -0.65
    æ©
    -0.62
    ãĥ¼ãĥĨãĤ£
    -0.60
     Catalog
    -0.60
    stown
    -0.60
     Gong
    -0.59
     Creed
    -0.58
    bay
    -0.58
    velength
    -0.57
    advertisement
    -0.57
    POSITIVE LOGITS
     wanna
    0.76
    umsy
    0.70
     missed
    0.70
     recess
    0.69
    otos
    0.68
     shenanigans
    0.67
    mys
    0.65
    izoph
    0.65
    ippers
    0.64
     accidentally
    0.64
    Act Density 0.039%

    No Known Activations