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

    Neuronpedia

    INDEX
    Explanations

    references to various types of tours and tour-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     colspan
    -0.61
     civile
    -0.56
    elser
    -0.56
    illère
    -0.55
     StringField
    -0.54
    PMG
    -0.54
    tidae
    -0.53
    iress
    -0.53
    autaire
    -0.52
    ecology
    -0.52
    POSITIVE LOGITS
    billon
    0.81
    istic
    0.71
    maline
    0.67
    Datuak
    0.65
     guides
    0.61
    naments
    0.59
     buses
    0.56
    AxisAlignment
    0.56
     guide
    0.55
     bus
    0.54
    Act Density 0.076%

    No Known Activations