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

    Neuronpedia

    INDEX
    Explanations

    mentions of snow and related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    eriksaan
    -0.73
     Eri
    -0.72
    SerializedSize
    -0.72
     agent
    -0.70
    DebuggerNonUser
    -0.70
     agents
    -0.69
     irmã
    -0.69
    AGENT
    -0.67
     Kult
    -0.66
    řez
    -0.65
    POSITIVE LOGITS
    snow
    1.52
     SNOW
    1.44
     Snow
    1.43
     snow
    1.41
    SNOW
    1.40
     Snowden
    1.37
    Snow
    1.34
     snows
    1.09
    snowy
    1.02
     snowboard
    1.02
    Act Density 0.008%

    No Known Activations