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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.68
    __":
    -0.66
    enderror
    -0.59
     yogur
    -0.59
     Likely
    -0.59
     {}),
    -0.58
    nextDouble
    -0.57
     Presumably
    -0.56
    Likely
    -0.56
    šanai
    -0.56
    POSITIVE LOGITS
     propOrder
    0.79
     themselves
    0.75
     or
    0.60
    themselves
    0.59
     simply
    0.57
    XtraEditors
    0.56
    kozó
    0.54
    bellar
    0.51
     whole
    0.50
     oder
    0.50
    Act Density 0.128%

    No Known Activations