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

    Neuronpedia

    INDEX
    Explanations

    the word "onto" and contextually relevant phrases about transfers or layers in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Houſe
    -0.74
     Anſ
    -0.72
     kebaya
    -0.70
     Jefus
    -0.70
     Мексичка
    -0.70
     Reſ
    -0.69
     étoient
    -0.69
    Accurate
    -0.69
    MessageTagHelper
    -0.69
     quelcon
    -0.68
    POSITIVE LOGITS
     concentrate
    0.86
     concentrated
    0.83
     Concentrate
    0.79
     Concentr
    0.77
     concentrates
    0.76
    Concentr
    0.76
    concentr
    0.75
     bull
    0.72
     onto
    0.70
     Bull
    0.62
    Act Density 0.074%

    No Known Activations