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

    Neuronpedia

    INDEX
    Explanations

    instances of the substring "con" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ùĩ
    -0.15
    andas
    -0.14
    ,'#
    -0.14
    dorf
    -0.14
    ieber
    -0.14
    obby
    -0.14
    .transitions
    -0.14
    dad
    -0.14
    dq
    -0.13
    dG
    -0.13
    POSITIVE LOGITS
    vention
    0.40
    ventional
    0.39
    tribution
    0.38
    venience
    0.37
    cern
    0.37
    crete
    0.37
    cepts
    0.35
    centration
    0.35
    venient
    0.35
    strained
    0.35
    Act Density 0.019%

    No Known Activations