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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xbb
    -0.17
    cbc
    -0.16
    xba
    -0.16
    xbc
    -0.15
    xeb
    -0.15
    xEB
    -0.14
    xDA
    -0.14
    ppv
    -0.14
    ddb
    -0.14
    xcd
    -0.14
    POSITIVE LOGITS
     MF
    0.69
     HF
    0.69
     NF
    0.68
     LF
    0.68
     SF
    0.68
     GF
    0.66
     VF
    0.66
     TF
    0.65
     PF
    0.65
     UF
    0.65
    Act Density 0.491%

    No Known Activations