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

    Neuronpedia

    INDEX
    Explanations

    instances of consensus or agreement among individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ytic
    -0.18
    خاÙĨÙĩ
    -0.18
    adge
    -0.16
     aggressive
    -0.15
    names
    -0.15
    élé
    -0.15
     Singer
    -0.14
    arker
    -0.14
    úc
    -0.14
     aggressively
    -0.14
    POSITIVE LOGITS
    ably
    0.26
    /dis
    0.24
    ance
    0.23
    able
    0.23
     upon
    0.22
    ement
    0.21
    大åĪ©
    0.20
    ging
    0.20
    EMENT
    0.20
    UpDown
    0.17
    Act Density 0.030%

    No Known Activations