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

    Neuronpedia

    INDEX
    Explanations

    terms related to contributions or donating

    oai_token-act-pair · gpt-3.5-turbo

    references to individual or collective contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.65
    Availability
    -0.63
    avis
    -0.63
    Ħ¢
    -0.60
     Rapt
    -0.60
    âĸ¬
    -0.59
    ATCH
    -0.58
     Missile
    -0.58
    ãĥĥãĥī
    -0.58
    isen
    -0.58
    POSITIVE LOGITS
     contribution
    0.83
     contribute
    0.82
     contributions
    0.79
    iosyncr
    0.78
    ertodd
    0.76
    jri
    0.74
     towards
    0.73
     Contributions
    0.72
    vernment
    0.72
    ificant
    0.69
    Act Density 0.023%

    No Known Activations