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

    Neuronpedia

    INDEX
    Explanations

    discussions of groups and conditions related to social dynamics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.81
     <<<<<<<<<<<<<<
    -0.78
     autorytatywna
    -0.78
    ✨:
    -0.71
    __':
    -0.70
    fjspx
    -0.69
    TagMode
    -0.69
    tonode
    -0.68
    }`).
    -0.68
    WarningLevel
    -0.68
    POSITIVE LOGITS
    Попис
    0.60
     itself
    0.54
     stessi
    0.52
     stesse
    0.50
     Itself
    0.49
     kendisi
    0.48
    roveň
    0.47
    Composable
    0.47
     stessa
    0.46
     herself
    0.46
    Act Density 1.195%

    No Known Activations