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

    Neuronpedia

    INDEX
    Explanations

    words related to assistance or support in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.88
    })));
    -0.79
     themſelves
    -0.77
     himſelf
    -0.75
    "]);
    -0.74
    '}>
    -0.73
     oneself
    -0.73
    \}\\
    -0.71
    "])
    -0.71
     Monfieur
    -0.71
    POSITIVE LOGITS
    AxisAlignment
    0.71
    การ
    0.66
    SerializedSize
    0.66
    tagHelperRunner
    0.65
    IntoConstraints
    0.63
     Drittan
    0.63
    ConstraintMaker
    0.63
    endregion
    0.60
     cikin
    0.60
     the
    0.58
    Act Density 0.201%

    No Known Activations