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

    Neuronpedia

    INDEX
    Explanations

    intensifiers or emphatic expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     very
    -0.37
     heat
    -0.30
     AFF
    -0.29
     lleva
    -0.28
     heavy
    -0.28
     muy
    -0.28
    very
    -0.27
     caché
    -0.27
     how
    -0.27
     processes
    -0.27
    POSITIVE LOGITS
     HasFactory
    0.80
    ValueStyle
    0.75
    #+#
    0.74
    Diwedd
    0.73
    IntoConstraints
    0.72
    +#+
    0.71
     ProtoMessage
    0.71
    expandindo
    0.69
    aarrggbb
    0.69
    principalTable
    0.68
    Act Density 0.004%

    No Known Activations