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

    Neuronpedia

    INDEX
    Explanations

    situations involving interactions between characters or entities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     виправивши
    -0.50
    TemporalType
    -0.48
    insee
    -0.45
    —
    -0.45
     home
    -0.44
    katu
    -0.44
     mer
    -0.43
    ="
    -0.42
    IH
    -0.42
     "'";
    -0.42
    POSITIVE LOGITS
    enderror
    0.72
     comigo
    0.69
    ècie
    0.69
    kegaard
    0.65
    érience
    0.64
     conmigo
    0.64
    SBATCH
    0.63
     continúas
    0.62
    ſelves
    0.62
    úgó
    0.60
    Act Density 0.065%

    No Known Activations