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

    Neuronpedia

    INDEX
    Explanations

    the word "one" and its variants, indicating a focus on singularity or specific instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.76
     صوتيه
    -0.53
    AndroidJUnit
    -0.52
    IntoConstraints
    -0.49
     respectively
    -0.47
    لاثة
    -0.46
     respectivamente
    -0.45
    ombic
    -0.44
    ראלי
    -0.43
    aminya
    -0.43
    POSITIVE LOGITS
     thing
    1.20
     reason
    1.15
     interesting
    1.04
     advantage
    0.97
     way
    0.95
     voordeel
    0.89
     benefit
    0.89
     important
    0.87
     drawback
    0.80
     difference
    0.80
    Act Density 0.331%

    No Known Activations