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

    Neuronpedia

    INDEX
    Explanations

    mentions of camping or camps

    oai_token-act-pair · gpt-3.5-turbo

    references to encampments or camps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.74
     regress
    -0.68
     nutrit
    -0.66
     platinum
    -0.65
     pudding
    -0.64
    ctive
    -0.63
     magnification
    -0.62
    hm
    -0.60
    piring
    -0.58
     wip
    -0.58
    POSITIVE LOGITS
    fires
    1.16
    ground
    1.16
    camp
    1.12
    grounds
    1.11
    fire
    1.06
     camp
    1.02
    agna
    1.01
    hor
    0.89
    agne
    0.89
    aign
    0.87
    Act Density 0.016%

    No Known Activations