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

    Neuronpedia

    INDEX
    Explanations

    words related to alternation or alternating actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilet
    -0.16
    gewater
    -0.15
    £
    -0.15
    ppe
    -0.15
    sonian
    -0.14
    aisy
    -0.14
    fighter
    -0.13
    zept
    -0.13
    anoia
    -0.13
    ulin
    -0.13
    POSITIVE LOGITS
    atives
    0.30
    ative
    0.25
    ately
    0.22
    atively
    0.20
    ativ
    0.19
     Altern
    0.19
    ATIVE
    0.18
    ating
    0.18
    Altern
    0.18
     altern
    0.18
    Act Density 0.008%

    No Known Activations