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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or absence of visibility and accessibility regarding objects or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.64
     <<<<<<<<<<<<<<
    -0.56
    GenerationType
    -0.51
     recommendation
    -0.49
     argued
    -0.49
    Portail
    -0.48
     numerus
    -0.48
    ोर्ट
    -0.45
     статья
    -0.44
    /*
    -0.43
    POSITIVE LOGITS
     glance
    0.78
     inspecting
    0.76
     inspection
    0.75
     glancing
    0.74
     inspect
    0.72
     observant
    0.72
     vistazo
    0.72
     magnifying
    0.68
     visual
    0.68
     peek
    0.68
    Act Density 0.427%

    No Known Activations