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

    Neuronpedia

    INDEX
    Explanations

    phrases that signal a lack of surprise or indicate expected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ello
    -0.17
    ener
    -0.15
     cust
    -0.15
    ITTER
    -0.15
    owler
    -0.15
    odia
    -0.15
    ymes
    -0.15
    Ú¾
    -0.14
     ind
    -0.14
    eten
    -0.14
    POSITIVE LOGITS
    prisingly
    0.35
    mount
    0.28
    prising
    0.28
    passed
    0.20
    iously
    0.20
    prs
    0.19
    veys
    0.18
    mounted
    0.18
    Mount
    0.18
     mounting
    0.18
    Act Density 0.004%

    No Known Activations