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

    Neuronpedia

    INDEX
    Explanations

    words describing thickness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.65
    Jereo
    -0.64
    ⓧ
    -0.63
    MessageOf
    -0.61
    SuppressMessage
    -0.61
    ichester
    -0.59
    ssaint
    -0.57
     defaultstate
    -0.56
     <<<<<<<<<<<<<<
    -0.56
    Vanjske
    -0.56
    POSITIVE LOGITS
     thick
    3.65
     Thick
    3.38
    thick
    3.32
    Thick
    3.29
     thicker
    2.98
     thickness
    2.67
     thicken
    2.67
     thickened
    2.50
     thickening
    2.44
    thickness
    2.37
    Act Density 0.079%

    No Known Activations