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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the basis or foundation of thoughts, decisions, or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assage
    -0.15
    coli
    -0.14
     bomb
    -0.14
    ombs
    -0.14
    Mahon
    -0.14
    åĩ¡
    -0.14
    ãĥ£
    -0.14
    μβ
    -0.13
    ryn
    -0.13
    uch
    -0.13
    POSITIVE LOGITS
    urb
    0.15
    ouce
    0.14
    edii
    0.14
    amin
    0.14
    éĺ
    0.13
    à¥Ĥà¤Ł
    0.13
    TOTYPE
    0.13
    apter
    0.13
    ngo
    0.13
    uria
    0.13
    Act Density 0.189%

    No Known Activations