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

    Neuronpedia

    INDEX
    Explanations

    words containing the substring 'er'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "er" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itionally
    -0.71
    hips
    -0.71
    enthal
    -0.69
    OUNT
    -0.69
    ership
    -0.68
    INESS
    -0.68
    IGHTS
    -0.64
    parency
    -0.64
    pring
    -0.64
    sense
    -0.63
    POSITIVE LOGITS
    asure
    0.95
    aser
    0.95
    asures
    0.93
    ogenous
    0.79
    rett
    0.77
     er
    0.76
    bers
    0.75
    icit
    0.75
    odox
    0.74
    asing
    0.74
    Act Density 0.005%

    No Known Activations