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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations containing the word "Springs"

    oai_token-act-pair · gpt-3.5-turbo

    references to various "Springs" locations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.86
    rons
    -0.85
    ctica
    -0.83
    ufact
    -0.76
    loss
    -0.72
    rity
    -0.70
    inance
    -0.70
    ism
    -0.68
    ISM
    -0.67
    istic
    -0.66
    POSITIVE LOGITS
     Springs
    0.98
    boro
    0.81
    dale
    0.77
    atoon
    0.74
    uits
    0.73
    hips
    0.69
    creen
    0.69
    ettings
    0.69
    hots
    0.68
    atche
    0.68
    Act Density 0.023%

    No Known Activations