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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuity and connection over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oho
    -0.17
    ohn
    -0.16
    antha
    -0.15
    antor
    -0.15
    cko
    -0.15
    agrid
    -0.15
    OpenHelper
    -0.14
    ibal
    -0.14
    combe
    -0.14
    erus
    -0.14
    POSITIVE LOGITS
    HING
    0.17
    ãĤ·ãĥ§ãĥ³
    0.15
    tü
    0.13
     BaseType
    0.13
     compat
    0.13
    ·»
    0.13
    son
    0.13
    ifo
    0.13
    -tm
    0.13
     addslashes
    0.13
    Act Density 0.004%

    No Known Activations